© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55196
    Prev
    Next
    INDEX
    Explanations

    ");

    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
     ↵↵↵
    -0.07
     cao
    -0.06
     türü
    -0.06
     hồi
    -0.06
     lobbyists
    -0.06
     creado
    -0.06
     tandem
    -0.06
    лок
    -0.06
     spotify
    -0.06
    inet
    -0.06
    POSITIVE LOGITS
     Pillow
    0.07
     filtr
    0.07
    ων
    0.07
    ेह
    0.06
    0.06
     collaborating
    0.06
    _short
    0.06
     sprint
    0.06
     TRUE
    0.06
    <|start_header_id|>
    0.06
    Activations Density 0.001%

    No Known Activations