© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43259
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on numeric tokens within algebraic or polynomial expressions.

    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
    .FormBorderStyle
    -0.07
     UITableViewDelegate
    -0.07
     Nath
    -0.07
    [y
    -0.06
     μπ
    -0.06
    111
    -0.06
    _male
    -0.06
    _walk
    -0.06
    .infinity
    -0.06
    .Type
    -0.06
    POSITIVE LOGITS
    ór
    0.06
    amina
    0.06
     attendant
    0.06
     şekilde
    0.06
     Львів
    0.06
    FE
    0.06
     werk
    0.06
    OLA
    0.06
     expended
    0.06
    ('~
    0.06
    Activations Density 0.002%

    No Known Activations