© 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. 11-RESID-POST-AA
    11. 46344
    Prev
    Next
    INDEX
    Explanations

    prime

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hookers
    -0.07
    rawn
    -0.07
    igor
    -0.06
     vorhand
    -0.06
    .dequeue
    -0.06
    -wide
    -0.06
    .firestore
    -0.06
     hit
    -0.06
     ขาย
    -0.06
     accelerometer
    -0.06
    POSITIVE LOGITS
     Supern
    0.08
    \Exception
    0.06
    CHOOL
    0.06
     bilateral
    0.06
     CString
    0.06
    UILT
    0.06
     primaries
    0.06
     nejen
    0.06
     تج
    0.06
     deductible
    0.06
    Activations Density 0.008%

    No Known Activations