© 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. 27-RESID-POST-AA
    11. 22321
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    атели
    -0.08
    ek
    -0.07
    ;!
    -0.07
     validating
    -0.06
     />
↵
    -0.06
     Gy
    -0.06
     Lý
    -0.06
    lops
    -0.06
    _pa
    -0.06
     Ob
    -0.06
    POSITIVE LOGITS
     audit
    0.07
    .two
    0.07
     dereg
    0.07
    iterr
    0.06
    _stock
    0.06
     Multi
    0.06
    ‌ان
    0.06
    ucht
    0.06
     blogs
    0.06
     Nice
    0.06
    Activations Density 0.037%

    No Known Activations