© 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. 89154
    Prev
    Next
    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash

    The neuron fires on the markers of direct dialogue—quotation marks and the words that begin spoken lines (e.g. “Mom,”)—i.e. it spots line openings of quoted speech.

    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
    ováním
    -0.07
     grounding
    -0.06
    -ing
    -0.06
    لت
    -0.06
    ########
    -0.06
    struk
    -0.06
    emption
    -0.06
    ести
    -0.06
    alculate
    -0.06
     Andersen
    -0.06
    POSITIVE LOGITS
     workplace
    0.07
     DISPLAY
    0.06
     UNITED
    0.06
    .');↵
    0.06
     '=
    0.06
     Communic
    0.06
    .Misc
    0.06
    ...↵↵
    0.06
     BadRequest
    0.06
     Rotation
    0.06
    Activations Density 0.039%

    No Known Activations