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. 104179
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Babies
    -0.07
    spo
    -0.07
    yy
    -0.06
    accine
    -0.06
    ژه
    -0.06
    色的
    -0.06
    ження
    -0.06
    ので
    -0.06
    submitted
    -0.06
     countertops
    -0.06
    POSITIVE LOGITS
    ..."↵↵
    0.06
    tero
    0.06
    bean
    0.06
    [op
    0.06
    _elements
    0.06
     #%
    0.06
    .mockito
    0.06
     carrots
    0.06
    ->___
    0.06
    =temp
    0.06
    Activations Density 1.094%

    No Known Activations