© 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. 52952
    Prev
    Next
    INDEX
    Explanations

    currently

    np_max-act · gemini-2.0-flash

    The neuron spots present‐tense statements of someone’s current role or status—e.g. the “is currently …” construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to professional sports figures, specifically their coaching and playing careers.

    oai_token-act-pair · gpt-4o-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
    AllowAnonymous
    -0.06
     Flores
    -0.06
     Razor
    -0.06
     ReadOnly
    -0.06
    concept
    -0.06
    Connect
    -0.06
     measuring
    -0.06
     “
    -0.06
    skirts
    -0.06
     Scotch
    -0.06
    POSITIVE LOGITS
    №№
    0.08
    <S
    0.06
    .chapter
    0.06
    _Item
    0.06
     //<
    0.06
    bookmark
    0.06
    (intent
    0.06
     Course
    0.06
     Correspond
    0.06
    (ans
    0.06
    Activations Density 0.017%

    No Known Activations