© 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. 23-RESID-POST-AA
    11. 64140
    Prev
    Next
    INDEX
    Explanations

    the ending is a vowel

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lexible
    -0.08
     commented
    -0.07
    epar
    -0.07
    師
    -0.07
    establish
    -0.07
    IO
    -0.07
    XML
    -0.06
     distribute
    -0.06
    'user
    -0.06
    Esc
    -0.06
    POSITIVE LOGITS
    μμε
    0.06
    losion
    0.06
     корм
    0.06
    なし
    0.06
    ptom
    0.06
     sửa
    0.06
    ゅ
    0.05
    ठन
    0.05
     muslim
    0.05
    駆
    0.05
    Activations Density 0.133%

    No Known Activations