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. 104206
    Prev
    Next
    INDEX
    Explanations

    Adjustments

    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
     tow
    -0.07
    Measure
    -0.07
     подіб
    -0.07
    (schedule
    -0.06
    .DotNetBar
    -0.06
    _timeout
    -0.06
     пацієн
    -0.06
    PARATOR
    -0.06
    StateManager
    -0.06
     Marshal
    -0.06
    POSITIVE LOGITS
    banks
    0.07
    sqrt
    0.06
    roti
    0.06
    roducing
    0.06
    FIELDS
    0.06
    abler
    0.06
    ử
    0.06
     ”↵
    0.06
    uitka
    0.05
     Liv
    0.05
    Activations Density 0.002%

    No Known Activations