© 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. 91473
    Prev
    Next
    INDEX
    Explanations

    fatty acids

    np_max-act · gemini-2.0-flash

    The neuron activates on the names (and fragments) of long-chain polyunsaturated fatty acids (e.g. “eicosapentaenoic acid,” “docosahexaenoic acid,” “arachidonic acid”).

    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
    จำ
    -0.07
    (utils
    -0.07
     cụ
    -0.07
    шь
    -0.06
    ového
    -0.06
     těchto
    -0.06
    зь
    -0.06
     할
    -0.06
    アイ
    -0.06
     सबस
    -0.06
    POSITIVE LOGITS
     photoshop
    0.07
     Workplace
    0.07
    accuracy
    0.07
    TextColor
    0.07
    .textColor
    0.07
    ";
    0.07
    month
    0.07
     crt
    0.06
    texture
    0.06
    ,long
    0.06
    Activations Density 0.002%

    No Known Activations