© 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. 64319
    Prev
    Next
    INDEX
    Explanations

    for

    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
    957
    -0.07
    ляется
    -0.07
    118
    -0.07
     restau
    -0.06
    hesion
    -0.06
     pleas
    -0.06
     HEADER
    -0.06
     Yen
    -0.06
     ---------------------------------------------------------------------------↵
    -0.06
     찬
    -0.06
    POSITIVE LOGITS
    -Man
    0.08
    ×↵↵
    0.07
    Bachelor
    0.07
     사이트
    0.07
     master
    0.07
     masters
    0.06
    .CharField
    0.06
    .userid
    0.06
    ابع
    0.06
    .SingleOrDefault
    0.06
    Activations Density 0.011%

    No Known Activations