© 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. 102241
    Prev
    Next
    INDEX
    Explanations

    -br

    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
    ця
    -0.07
     lanes
    -0.07
    Inf
    -0.07
    444
    -0.07
    .pp
    -0.07
    .range
    -0.06
    ural
    -0.06
     Αγγ
    -0.06
     softer
    -0.06
    Ђ
    -0.06
    POSITIVE LOGITS
     чес
    0.06
    "'↵
    0.06
     modelos
    0.06
     ""))↵
    0.06
     Nimbus
    0.06
    *e
    0.06
    .MODEL
    0.06
    래스
    0.06
    .intValue
    0.06
     balances
    0.06
    Activations Density 0.237%

    No Known Activations