© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30216
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens appearing in Wikipedia “Category:” metadata lines (e.g. words like “United,” “Community,” etc., in the category tags).

    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
    VES
    -0.08
    ves
    -0.07
    Players
    -0.06
    —in
    -0.06
     организ
    -0.06
    iết
    -0.06
     수도
    -0.06
     яс
    -0.06
    ství
    -0.06
    /
↵
    -0.06
    POSITIVE LOGITS
    변
    0.07
     mortality
    0.07
     astonishing
    0.07
     fortunate
    0.07
     woes
    0.07
    viewport
    0.06
    ptides
    0.06
     perverse
    0.06
    liqu
    0.06
    交流
    0.06
    Activations Density 0.005%

    No Known Activations