© 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. 73607
    Prev
    Next
    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative cooking‐instruction verbs—especially dough-handling actions like “roll,” “out,” “knead,” “fold,” etc.

    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
    ater
    -0.06
     sıras
    -0.06
    랙
    -0.06
    .worker
    -0.06
    Chicken
    -0.06
    \uff
    -0.06
     SVN
    -0.06
    orro
    -0.06
    -u
    -0.06
    .ham
    -0.06
    POSITIVE LOGITS
     :)↵↵
    0.07
     estimated
    0.07
    abol
    0.06
     látky
    0.06
    �名
    0.06
     Elizabeth
    0.06
    .'↵↵
    0.06
    UniqueId
    0.06
    NESS
    0.06
     );↵↵
    0.06
    Activations Density 0.002%

    No Known Activations