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. 104046
    Prev
    Next
    INDEX
    Explanations

    Scientific notation/symbols

    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
     Sector
    -0.07
     Berlin
    -0.06
    !」
    -0.06
     Operators
    -0.06
    arks
    -0.06
    eca
    -0.06
    Template
    -0.06
     towns
    -0.06
    ility
    -0.06
    Stats
    -0.06
    POSITIVE LOGITS
    (
    ↵
    0.07
    Apparently
    0.07
    _PROVID
    0.06
    �
    0.06
     judged
    0.06
    kemiz
    0.06
    (↵↵
    0.06
    参与
    0.06
    !!)↵
    0.06
     Sequ
    0.06
    Activations Density 0.076%

    No Known Activations