Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 104439
    Prev
    Next
    INDEX
    Explanations

    product description

    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
     gobierno
    -0.08
     med
    -0.07
    Hello
    -0.07
     lean
    -0.07
    ('
    -0.06
    Days
    -0.06
     proves
    -0.06
     bunker
    -0.06
    dto
    -0.06
     strongest
    -0.06
    POSITIVE LOGITS
     legis
    0.07
    örü
    0.06
     دس
    0.06
     obrig
    0.06
    const
    0.06
    ваем
    0.06
     constituent
    0.06
    ateway
    0.06
    inç
    0.06
    .Payment
    0.06
    Activations Density 0.015%

    No Known Activations