© 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. 74084
    Prev
    Next
    INDEX
    Explanations

    Code, configuration files

    np_max-act · gemini-2.0-flash

    The neuron lights up on numeric tokens (digits and numbers).

    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
     від
    -0.07
    Instagram
    -0.07
    .lambda
    -0.07
    -final
    -0.07
     กรก
    -0.06
    ，看
    -0.06
    Italic
    -0.06
    (engine
    -0.06
    THR
    -0.06
    queries
    -0.06
    POSITIVE LOGITS
    ittings
    0.07
     Στα
    0.06
    sorted
    0.06
    การใช
    0.06
     Survivor
    0.06
     육
    0.06
    全面
    0.06
     NotSupportedException
    0.05
    722
    0.05
     satisf
    0.05
    Activations Density 0.023%

    No Known Activations