© 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. 19-RESID-POST-AA
    6. 71122
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
     policymakers
    -0.07
    baum
    -0.07
     Nob
    -0.07
     kurul
    -0.06
     chamber
    -0.06
     eastern
    -0.06
    _INTERFACE
    -0.06
    ():↵↵
    -0.06
    ín
    -0.06
     educators
    -0.06
    POSITIVE LOGITS
    upply
    0.07
    ्रद
    0.06
    fails
    0.06
    /op
    0.06
    .prop
    0.06
     AX
    0.06
    leşme
    0.06
    getWindow
    0.06
    연
    0.06
     кисл
    0.06
    Activations Density 0.027%

    No Known Activations