© 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. 7979
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “willing” (as in “willing to …”) indicating expressions of willingness or determination.

    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
    二二二二
    -0.07
     اص
    -0.07
    _BOOT
    -0.06
     tách
    -0.06
     Huffman
    -0.06
     JavaScript
    -0.06
     ker
    -0.06
    üyordu
    -0.06
    ,text
    -0.06
    ικών
    -0.06
    POSITIVE LOGITS
     kat
    0.07
    <hr
    0.06
    cretion
    0.06
    QA
    0.06
     imaginable
    0.06
    dr
    0.06
     Organizations
    0.06
    _interp
    0.06
     fatt
    0.06
    openh
    0.06
    Activations Density 0.012%

    No Known Activations