© 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. 27-RESID-POST-AA
    11. 46919
    Prev
    Next
    INDEX
    Explanations

    supermarket chains

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podmínek
    -0.07
    几
    -0.07
     última
    -0.07
    Ｄ
    -0.07
    ава
    -0.07
    '(
    -0.06
     IO
    -0.06
     forth
    -0.06
     alleges
    -0.06
     certain
    -0.06
    POSITIVE LOGITS
    <object
    0.07
    .geometry
    0.06
    aneous
    0.06
    .webkit
    0.06
     Rever
    0.06
    гор
    0.06
    ット
    0.06
    "github
    0.06
    _ind
    0.06
    lots
    0.06
    Activations Density 0.038%

    No Known Activations