© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 71263
    Prev
    Next
    INDEX
    Explanations

    put

    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
    >Your
    -0.07
    enth
    -0.07
     paylaş
    -0.06
    199
    -0.06
    běh
    -0.06
    ocial
    -0.06
     články
    -0.06
    вест
    -0.06
    _operator
    -0.06
     basal
    -0.06
    POSITIVE LOGITS
     aque
    0.07
    afka
    0.06
     capable
    0.06
     face
    0.06
    Rotation
    0.06
     Gloves
    0.06
     frac
    0.06
     cade
    0.06
    _grad
    0.06
    getStringExtra
    0.06
    Activations Density 0.019%

    No Known Activations