© 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. 6329
    Prev
    Next
    INDEX
    Explanations

    quantum

    np_max-act · gemini-2.0-flash

    This neuron principally activates on the word “quantum” (and closely related technical terms) in the text.

    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
     Fort
    -0.07
    hend
    -0.06
    haul
    -0.06
    -Bar
    -0.06
    nowrap
    -0.06
    aginator
    -0.06
     Ashe
    -0.06
     ivory
    -0.06
    _SLOT
    -0.06
     appeared
    -0.06
    POSITIVE LOGITS
    /auth
    0.07
    ým
    0.07
     discard
    0.07
     несколь
    0.07
    );*/↵
    0.07
    (socket
    0.06
     conjug
    0.06
     defining
    0.06
    umni
    0.06
    excluding
    0.06
    Activations Density 0.005%

    No Known Activations