© 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
    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. 125216
    Prev
    Next
    INDEX
    Explanations

    ud

    np_max-act · gemini-2.0-flash

    The neuron fires on documentary “metadata” tokens used in the markdown/HTML (e.g. UD_<language>-PUD identifiers, `href=` and the fragments of link URLs like file names and POS-tag codes).

    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
     Updates
    -0.06
    '])){
    -0.06
    _DO
    -0.06
    测试
    -0.06
     blades
    -0.06
    -Version
    -0.06
    ≡≡
    -0.06
    culus
    -0.06
     protagonists
    -0.06
     Girls
    -0.06
    POSITIVE LOGITS
    still
    0.07
     рахунок
    0.07
     Saying
    0.06
    chn
    0.06
    jr
    0.06
    gal
    0.06
    _bn
    0.06
    Holder
    0.06
    lider
    0.06
    幸福
    0.06
    Activations Density 0.000%

    No Known Activations