© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128615
    Prev
    Next
    INDEX
    Explanations

    elle

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the substring “appelle,” as in “appellant” or “appellee,” in legal case text.

    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
    take
    -0.07
    도의
    -0.07
    ْت
    -0.06
    _DIRECT
    -0.06
    ceed
    -0.06
    、:
    -0.06
     Johannesburg
    -0.06
    wr
    -0.06
    猜
    -0.06
    urt
    -0.06
    POSITIVE LOGITS
     aún
    0.06
    /log
    0.06
     لق
    0.06
    kiem
    0.06
     ویژگی
    0.06
     RaycastHit
    0.06
    Downloader
    0.06
     Katie
    0.06
     predis
    0.06
     adventurer
    0.06
    Activations Density 0.003%

    No Known Activations