© 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. 6391
    Prev
    Next
    INDEX
    Explanations

    coal

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of the coal industry (e.g., “coal” and related contexts).

    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
    _B
    -0.07
     Cuisine
    -0.06
    urse
    -0.06
    YA
    -0.06
    AY
    -0.06
     mùi
    -0.06
     optic
    -0.06
     rupture
    -0.06
     lên
    -0.06
     seemed
    -0.06
    POSITIVE LOGITS
    三级
    0.08
     معد
    0.07
    /apimachinery
    0.07
    怖
    0.07
     передбач
    0.07
     Gingrich
    0.07
    ทางการ
    0.06
    RuleContext
    0.06
    __(
    0.06
    اعد
    0.06
    Activations Density 0.038%

    No Known Activations