Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 127334
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mana
    -0.07
     organization
    -0.07
    privileged
    -0.07
    regar
    -0.07
    charging
    -0.06
    /run
    -0.06
    ent
    -0.06
    missions
    -0.06
     dụ
    -0.06
     ziy
    -0.06
    POSITIVE LOGITS
    Named
    0.07
    Trader
    0.07
     Restaurant
    0.06
     haystack
    0.06
    .jpa
    0.06
    (pop
    0.06
     terug
    0.06
    StringEncoding
    0.06
     actionBar
    0.06
    PasswordField
    0.06
    Activations Density 0.023%

    No Known Activations