© 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. 7-RESID-POST-AA
    11. 113171
    Prev
    Next
    INDEX
    Explanations

    Because

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sta
    -0.06
    ért
    -0.06
     Hungary
    -0.06
    MethodImpl
    -0.06
    .hu
    -0.06
    štění
    -0.06
    &nbsp
    -0.06
    /menu
    -0.06
    inston
    -0.06
    emark
    -0.06
    POSITIVE LOGITS
     –↵↵
    0.07
     sweaty
    0.07
    ？”↵↵
    0.07
    _________________↵↵
    0.07
    Conv
    0.06
     Since
    0.06
    ()↵↵↵↵
    0.06
    .'.$
    0.06
     Searching
    0.06
     Visualization
    0.06
    Activations Density 0.022%

    No Known Activations