© 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. 83803
    Prev
    Next
    INDEX
    Explanations

    share

    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
     Wenn
    -0.07
    <Game
    -0.07
     Porter
    -0.07
    .Author
    -0.06
    rokes
    -0.06
    ler
    -0.06
    153
    -0.06
    apor
    -0.06
    -(
    -0.06
    (sd
    -0.06
    POSITIVE LOGITS
     comparatively
    0.06
     Paolo
    0.06
     damages
    0.06
     prohibits
    0.06
    inished
    0.06
    igmatic
    0.06
    bis
    0.06
     behold
    0.06
     شهید
    0.05
     Morrow
    0.05
    Activations Density 0.047%

    No Known Activations