© 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
    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. 13533
    Prev
    Next
    INDEX
    Explanations

    atomic

    np_max-act · gemini-2.0-flash

    This neuron activates on technical terms related to atomic physics and spectroscopy, such as mentions of “atomic,” “transition,” and “spectro-”/“scopic” descriptors.

    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
     nozzle
    -0.07
    nova
    -0.07
    etadata
    -0.07
    	M
    -0.07
     Zar
    -0.07
    PFN
    -0.06
    	TArray
    -0.06
     AV
    -0.06
     meinem
    -0.06
     kond
    -0.06
    POSITIVE LOGITS
     业
    0.07
    游
    0.07
    amentals
    0.07
    ".
    0.06
     )))
    0.06
    !
    0.06
     Egyptian
    0.06
    ुच
    0.05
     vụ
    0.05
    рив
    0.05
    Activations Density 0.010%

    No Known Activations