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. 15-RESID-POST-AA
    6. 21393
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
     اجر
    -0.07
     thorough
    -0.07
     표시
    -0.06
     notamment
    -0.06
    major
    -0.06
    absolute
    -0.06
    )y
    -0.06
     shear
    -0.06
    .Tensor
    -0.06
    aternion
    -0.06
    POSITIVE LOGITS
    lags
    0.07
    Так
    0.07
    责
    0.07
     Так
    0.07
    ск
    0.07
    _RUN
    0.07
    TRANS
    0.07
    Start
    0.07
    JO
    0.07
    ervlet
    0.07
    Activations Density 2.719%

    No Known Activations