© 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. 109233
    Prev
    Next
    INDEX
    Explanations

    station

    np_max-act · gemini-2.0-flash

    The neuron spikes on imperative task steps—phrases specifying actions to perform (e.g. “Collect the nightshades,” “Obtain a blessing,” “Defeat the ogre”).

    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
    frame
    -0.07
    Front
    -0.07
    (f
    -0.07
    щее
    -0.07
    .col
    -0.07
     biểu
    -0.06
     Destruction
    -0.06
    ader
    -0.06
    _ring
    -0.06
     compared
    -0.06
    POSITIVE LOGITS
    .sell
    0.07
     засід
    0.06
     generosity
    0.06
    ');
↵
    0.06
    wap
    0.06
    áct
    0.06
    wy
    0.06
    صب
    0.06
     stripslashes
    0.06
    .controllers
    0.06
    Activations Density 0.006%

    No Known Activations