© 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. 3-RESID-POST-AA
    6. 95349
    Prev
    Next
    INDEX
    Explanations

    izing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tant
    -0.07
    delegate
    -0.06
     querying
    -0.06
     verg
    -0.06
     resist
    -0.06
    _MISSING
    -0.06
     mie
    -0.06
    <Value
    -0.06
     accidentally
    -0.06
    าณ
    -0.06
    POSITIVE LOGITS
    acies
    0.07
    .GraphicsUnit
    0.06
    che
    0.06
    ализ
    0.06
    acas
    0.06
    489
    0.06
    早
    0.06
    249
    0.06
    uate
    0.06
    лей
    0.06
    Activations Density 0.003%

    No Known Activations