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. 21563
    Prev
    Next
    INDEX
    Explanations

    close

    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
    实施
    -0.08
     반
    -0.07
     toda
    -0.07
    760
    -0.06
     disob
    -0.06
    aty
    -0.06
     verdienen
    -0.06
    adera
    -0.06
    opak
    -0.06
     ним
    -0.06
    POSITIVE LOGITS
     Guards
    0.07
     professions
    0.07
    .Claims
    0.07
    .Book
    0.06
    armac
    0.06
    Plug
    0.06
     keeping
    0.06
    ovies
    0.06
    Catch
    0.06
     Films
    0.06
    Activations Density 0.004%

    No Known Activations