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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6410
    Prev
    Next
    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash

    This neuron fires on underscore tokens—e.g. standalone `_` wildcards or underscores in identifiers—marking places in code where `_` appears.

    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
    Mar
    -0.07
     claws
    -0.06
     crater
    -0.06
     א
    -0.06
     Describe
    -0.06
     golf
    -0.06
     recruits
    -0.06
     ",
    ↵
    -0.06
     Tunisia
    -0.06
     Sic
    -0.06
    POSITIVE LOGITS
     _.
    0.07
    .onreadystatechange
    0.06
    lotte
    0.06
     Kč
    0.06
    ruby
    0.06
    _performance
    0.06
    _DIRECTORY
    0.06
    leaning
    0.06
    _BGR
    0.06
     Formatting
    0.06
    Activations Density 0.002%

    No Known Activations