© 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. 15-RESID-POST-AA
    11. 37685
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _changes
    -0.07
    _stand
    -0.07
     birey
    -0.07
    zen
    -0.07
     camp
    -0.06
     helpless
    -0.06
    cr
    -0.06
    Arrow
    -0.06
     droit
    -0.06
     BitSet
    -0.06
    POSITIVE LOGITS
     мот
    0.07
    ([[
    0.06
    онь
    0.06
     stalk
    0.06
     вод
    0.06
     kategor
    0.06
     MOZ
    0.06
    .setPassword
    0.06
    acia
    0.06
     mdi
    0.06
    Activations Density 0.000%

    No Known Activations