© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44311
    Prev
    Next
    INDEX
    Explanations

    natural resources

    np_max-act · gemini-2.0-flash

    Same activations, but with all zeros filtered out: <start> rich 1.6318359375 natural 2.533203125 resources 2.568359375 coal 0.98828125 natural 1.1328125 gas 0.83154296875 minerals 1.6875 miner 1.826171875 rich 1.9794921875 resources 2.572265625 natural 2.267578125 resources 2.361328125 reserv 1.3798828125 gas 2.578125 pet 0.87841796875 róleo 0.64306640625 <end> Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of abundance or richness in natural resources.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gay
    -0.07
    umed
    -0.07
    เฉ
    -0.06
    pref
    -0.06
    ворю
    -0.06
     setTitleColor
    -0.06
     H�
    -0.06
     blades
    -0.06
    (dim
    -0.06
    culated
    -0.06
    POSITIVE LOGITS
     pakistan
    0.07
     NavBar
    0.07
    !="
    0.07
     Auto
    0.06
     ^{°}
    0.06
     住
    0.06
     Methods
    0.06
     "'.$
    0.06
     Disneyland
    0.06
     isEmpty
    0.06
    Activations Density 0.040%

    No Known Activations