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

    Neuronpedia

    Jacobian LensNEW
    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. 38056
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on words and punctuation in the email “Subject:” header, identifying tokens that belong to the subject line.

    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
    就算
    -0.07
    ivial
    -0.06
    Spawn
    -0.06
    ах
    -0.06
     multiplying
    -0.06
    ้อม
    -0.06
     segundo
    -0.06
     représent
    -0.06
    ับผ
    -0.06
     decrement
    -0.06
    POSITIVE LOGITS
     επα
    0.07
    mond
    0.06
    /packages
    0.06
     incumb
    0.06
     […]↵
    0.06
    .inc
    0.05
    斷
    0.05
    Questions
    0.05
     relates
    0.05
    idency
    0.05
    Activations Density 0.010%

    No Known Activations