© 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. 85717
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash

    The neuron triggers on empty‐parameter parentheses “()” in code, e.g. no-argument method or constructor declarations.

    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
    霞
    -0.07
     unserialize
    -0.07
     Razor
    -0.06
     select
    -0.06
    getEmail
    -0.06
     Ps
    -0.06
    Content
    -0.06
    uctose
    -0.06
     کننده
    -0.06
    byname
    -0.06
    POSITIVE LOGITS
    нак
    0.07
    bob
    0.07
    [model
    0.07
    '_
    0.06
    quette
    0.06
    lli
    0.06
    šlo
    0.06
    BASH
    0.06
    unal
    0.06
    ／／
    0.06
    Activations Density 0.005%

    No Known Activations