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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 78667
    Prev
    Next
    INDEX
    Explanations

    Political figures, terms in office

    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
    -scripts
    -0.07
     looping
    -0.07
     предвар
    -0.07
     array
    -0.07
    .Formatter
    -0.06
     needles
    -0.06
     midnight
    -0.06
     asked
    -0.06
     Já
    -0.06
     अव
    -0.06
    POSITIVE LOGITS
    191
    0.08
    192
    0.07
    197
    0.06
    190
    0.06
    леч
    0.06
     Fiat
    0.06
    196
    0.06
     Maison
    0.06
    193
    0.06
    ToolTip
    0.06
    Activations Density 0.018%

    No Known Activations