Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129487
    Prev
    Next
    INDEX
    Explanations

    news headlines

    np_max-act · gemini-2.0-flash

    The main thing this neuron detects is phrases describing something becoming, increasing, or gaining (i.e., a change or addition).

    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
    ----
    -0.07
    "While
    -0.06
    -associated
    -0.06
    _LOW
    -0.06
    "E
    -0.06
    failed
    -0.06
     �
    -0.06
    	temp
    -0.06
    (pm
    -0.06
    됩니다
    -0.06
    POSITIVE LOGITS
     растений
    0.06
    reature
    0.06
     ));↵
    0.06
    ς
    0.06
    岛
    0.06
    ControlItem
    0.06
    .minutes
    0.06
     ResultSet
    0.06
    tion
    0.06
    orption
    0.06
    Activations Density 0.103%

    No Known Activations