Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80656
    Prev
    Next
    INDEX
    Explanations

    false

    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
    Not in Any Lists

    No Comments

    Negative Logits
     depreci
    -0.07
    .Op
    -0.06
    _between
    -0.06
    棋
    -0.06
    렇게
    -0.06
    outlined
    -0.06
    .metroLabel
    -0.06
     nâng
    -0.06
     reuseIdentifier
    -0.06
    _ENCODING
    -0.06
    POSITIVE LOGITS
     Rencontres
    0.07
    ...
    ↵
    0.06
    alaria
    0.06
    .management
    0.06
    atk
    0.06
     defaultdict
    0.06
    dıktan
    0.06
     magnetic
    0.06
    jin
    0.06
    电子
    0.05
    Activations Density 0.005%

    No Known Activations