© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92221
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash

    The neuron fires on common auxiliary and copular verbs (e.g. “is,” “will,” “es,” etc.) that often introduce questions or evaluative clauses.

    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
    (horizontal
    -0.07
     goofy
    -0.07
    质
    -0.07
    .Skin
    -0.06
     caric
    -0.06
    OCI
    -0.06
    (ev
    -0.06
     Slov
    -0.06
    bearer
    -0.06
    /sec
    -0.06
    POSITIVE LOGITS
    $",
    0.06
    iring
    0.06
    _verify
    0.06
    lung
    0.06
     ELECT
    0.06
    currentPage
    0.06
    Expense
    0.06
     Market
    0.06
    _VENDOR
    0.06
    ........................
    0.06
    Activations Density 0.492%

    No Known Activations