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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 31623
    Prev
    Next
    INDEX
    Explanations

    Frame

    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
    efficient
    -0.07
     nc
    -0.07
    ISP
    -0.07
    .SC
    -0.07
    ?type
    -0.07
    ผ
    -0.06
     hé
    -0.06
     반
    -0.06
    เตร
    -0.06
     ž
    -0.06
    POSITIVE LOGITS
     tiế
    0.06
    icken
    0.06
    _published
    0.06
    iversal
    0.06
     Carpenter
    0.06
    idepress
    0.06
    abbix
    0.06
    <
    0.06
    .ToolStrip
    0.06
    OW
    0.06
    Activations Density 0.007%

    No Known Activations