© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2592
    Prev
    Next
    INDEX
    Explanations

    code and logs

    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
    compile
    -0.08
    follower
    -0.07
    "c
    -0.07
    recur
    -0.06
    stdint
    -0.06
    .lot
    -0.06
    _lp
    -0.06
     пропози
    -0.06
    Literal
    -0.06
    represent
    -0.06
    POSITIVE LOGITS
    аблиц
    0.08
    .Att
    0.07
    =========↵
    0.06
    税
    0.06
     ortam
    0.06
    .Book
    0.06
     bone
    0.06
    .
↵
    0.06
     IPv
    0.06
     onslaught
    0.06
    Activations Density 0.069%

    No Known Activations