© 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. 23-RESID-POST-AA
    6. 7917
    Prev
    Next
    INDEX
    Explanations

    set

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GEN
    -0.07
    typically
    -0.07
    ugg
    -0.06
    سازی
    -0.06
    apters
    -0.06
     magna
    -0.06
    ユ
    -0.06
    ew
    -0.06
     TOOL
    -0.06
    AccountId
    -0.06
    POSITIVE LOGITS
     Indeed
    0.07
     Decorating
    0.07
    veal
    0.06
     appreciation
    0.06
     $('.
    0.06
     render
    0.06
     peně
    0.06
    广
    0.06
     teamwork
    0.06
     aktivit
    0.06
    Activations Density 0.004%

    No Known Activations