© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 19-RESID-POST-AA
    11. 108114
    Prev
    Next
    INDEX
    Explanations

    Thr

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    LOC
    -0.07
    level
    -0.07
    _average
    -0.07
    ennon
    -0.06
    ective
    -0.06
    συ
    -0.06
    sticks
    -0.06
    String
    -0.06
    occasion
    -0.06
    ocyte
    -0.06
    POSITIVE LOGITS
    -be
    0.06
    HC
    0.06
    (attrs
    0.06
     드립니다
    0.06
    англ
    0.06
     дина
    0.06
    }↵↵
    0.06
    _FLASH
    0.06
    .keep
    0.06
     inspiration
    0.06
    Activations Density 0.004%

    No Known Activations