© 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. 43261
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    The neuron fires on content‐heavy, domain‐specific tokens (not common function words) such as technical or scholarly terms and punctuation that mark formal, informational text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     Tours
    -0.07
     outrage
    -0.06
     Pun
    -0.06
    mallow
    -0.06
     Walnut
    -0.06
     rc
    -0.06
     завжди
    -0.06
     Musik
    -0.06
     навч
    -0.06
     samples
    -0.06
    POSITIVE LOGITS
    /google
    0.06
    percentage
    0.06
     unsuccessfully
    0.06
    :class
    0.06
    .success
    0.06
    افة
    0.06
    ły
    0.06
    ्रब
    0.06
    ình
    0.06
     filtered
    0.06
    Activations Density 0.073%

    No Known Activations