© 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. 110710
    Prev
    Next
    INDEX
    Explanations

    elections and membership

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on tokens conveying numeric information—dates, counts, quantities, and other number-related terms.

    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
     đọ
    -0.07
     Cab
    -0.07
     záznam
    -0.07
     cmd
    -0.07
    camatan
    -0.06
     Lehr
    -0.06
     за
    -0.06
    最新
    -0.06
    atement
    -0.06
    ToDate
    -0.06
    POSITIVE LOGITS
     tabi
    0.07
    	al
    0.06
     polov
    0.06
    dim
    0.06
    BACKGROUND
    0.06
     constrain
    0.06
    rounded
    0.06
    лаз
    0.06
    .");
    0.06
    imits
    0.06
    Activations Density 0.016%

    No Known Activations