© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 25045
    Prev
    Next
    INDEX
    Explanations

    restaurants and bars

    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
    picture
    -0.07
    _formula
    -0.07
     ब
    -0.07
    093
    -0.06
    bett
    -0.06
     leather
    -0.06
    _minus
    -0.06
    े,
    -0.06
    _py
    -0.06
    .capture
    -0.06
    POSITIVE LOGITS
     hereby
    0.07
    >";
    0.07
    contres
    0.06
     swingerclub
    0.06
     Inherits
    0.06
    겠
    0.06
    (Window
    0.06
    toMatch
    0.06
     Proceed
    0.06
     fø
    0.06
    Activations Density 0.042%

    No Known Activations