© 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. 11-RESID-POST-AA
    11. 101138
    Prev
    Next
    INDEX
    Explanations

    dissip

    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
    Negative Logits
    標
    -0.07
    ĞI
    -0.07
     key
    -0.07
    <header
    -0.07
    .key
    -0.06
    .Mod
    -0.06
    .Free
    -0.06
     Geo
    -0.06
    \Backend
    -0.06
     YM
    -0.06
    POSITIVE LOGITS
     dissip
    0.11
     dissolve
    0.10
     dissolved
    0.09
     diss
    0.09
     dissent
    0.09
     dissolution
    0.09
    abol
    0.09
     Diss
    0.08
    laps
    0.08
     dissoci
    0.08
    Activations Density 0.007%

    No Known Activations