© 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
    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. 44581
    Prev
    Next
    INDEX
    Explanations

    hyphens/pipes

    np_max-act · gemini-2.0-flash

    The neuron fires on the kind of punctuation, separators, and capitalized tokens you see in headlines and article metadata (e.g. “|”, “–”, title‐cased words, bylines).

    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
    .ignore
    -0.07
    (Render
    -0.07
    (key
    -0.07
    قع
    -0.06
    _field
    -0.06
    ,g
    -0.06
     proverb
    -0.06
     spy
    -0.06
     foe
    -0.06
     дея
    -0.06
    POSITIVE LOGITS
     Suites
    0.06
     contextual
    0.06
     국내
    0.06
    Accessible
    0.06
    إن
    0.06
     chosen
    0.06
    /views
    0.06
     Celebration
    0.06
     Ivanka
    0.06
     empres
    0.06
    Activations Density 0.022%

    No Known Activations