© 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. 23-RESID-POST-AA
    11. 63078
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ja
    -0.07
     contro
    -0.06
    addr
    -0.06
     AIS
    -0.06
    dbc
    -0.06
     Між
    -0.06
     necessário
    -0.06
     Furn
    -0.06
     boobs
    -0.06
    mins
    -0.06
    POSITIVE LOGITS
    ＼＼
    0.07
    .textColor
    0.07
    )++;↵
    0.07
    (create
    0.07
    .ResultSet
    0.06
    .apply
    0.06
    .myapplication
    0.06
     Header
    0.06
     Robin
    0.06
     سرمایه
    0.06
    Activations Density 0.091%

    No Known Activations