© 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 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. 23880
    Prev
    Next
    INDEX
    Explanations

    Animation

    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
     Tick
    -0.07
     pouvez
    -0.07
    ět
    -0.06
     ích
    -0.06
    Lot
    -0.06
     Surgical
    -0.06
    (high
    -0.06
     GRAT
    -0.06
    Friends
    -0.06
    Pick
    -0.06
    POSITIVE LOGITS
    =F
    0.07
     nova
    0.06
    .Skip
    0.06
    pective
    0.06
     uvědom
    0.06
     styles
    0.06
    richText
    0.06
     silently
    0.06
    WithContext
    0.06
    나무
    0.06
    Activations Density 0.100%

    No Known Activations