© 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. 7578
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on JavaScript event‐handler names (e.g. the string labels like "data", "end", "response", etc., passed to `.on` calls).

    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
     Lawson
    -0.07
     cottage
    -0.07
     contraception
    -0.06
    ottage
    -0.06
    _compat
    -0.06
    _Tick
    -0.06
    .PL
    -0.06
     plotting
    -0.06
     undermined
    -0.06
    拓
    -0.06
    POSITIVE LOGITS
    .eu
    0.06
    乃
    0.06
    FilePath
    0.06
    edicine
    0.06
    _SE
    0.06
    .v
    0.06
     테
    0.06
     nejlepší
    0.06
     Caught
    0.06
     captures
    0.06
    Activations Density 0.012%

    No Known Activations