© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25206
    Prev
    Next
    INDEX
    Explanations

    Code and web data

    np_max-act · gemini-2.0-flash

    programming-related identifiers and library/class or package names (especially mixed-case or underscore/dotted code tokens)

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     roulette
    -0.07
    ump
    -0.07
    packages
    -0.06
    blr
    -0.06
    409
    -0.06
    enso
    -0.06
     Something
    -0.06
    bounding
    -0.06
    ывания
    -0.06
     Glide
    -0.06
    POSITIVE LOGITS
    <G
    0.07
    (dt
    0.07
    figcaption
    0.06
    [tid
    0.06
    stadt
    0.06
    \(
    0.06
     adorable
    0.06
     Candid
    0.06
     gerçekleştir
    0.06
    edn
    0.06
    Activations Density 1.307%

    No Known Activations