© 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. 55601
    Prev
    Next
    INDEX
    Explanations

    early life biographies

    np_max-act · gemini-2.0-flash

    This neuron fires on biographical narrative cues—tokens describing early‐life background and formative events (e.g. “showed,” “interest,” “age,” “began,” “memoriz­ing,” etc.).

    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
    _data
    -0.07
    ौत
    -0.06
    semble
    -0.06
    595
    -0.06
    .fail
    -0.06
    (status
    -0.06
    需
    -0.06
    .before
    -0.06
    ta
    -0.06
    [path
    -0.06
    POSITIVE LOGITS
    gil
    0.06
     apresent
    0.06
    ialias
    0.06
     серьез
    0.06
    ?action
    0.06
     Bryant
    0.06
     Rpc
    0.06
    )){
    0.06
    sanitize
    0.06
    uitive
    0.06
    Activations Density 0.036%

    No Known Activations