© 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. 128545
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal 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
     conce
    -0.07
     attendee
    -0.06
     وف
    -0.06
     needy
    -0.06
     pickups
    -0.06
    IGO
    -0.06
     nostr
    -0.06
    peri
    -0.06
     plastic
    -0.06
    .neg
    -0.06
    POSITIVE LOGITS
    _dimension
    0.07
    جل
    0.06
     clearInterval
    0.06
     ')'
    0.06
    sage
    0.06
     місті
    0.06
    ям
    0.06
    ...↵↵↵↵↵↵
    0.06
     **/↵↵
    0.06
    ."↵↵↵↵
    0.06
    Activations Density 0.060%

    No Known Activations