© 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. 68568
    Prev
    Next
    INDEX
    Explanations

    rem

    np_max-act · gemini-2.0-flash

    This neuron detects Windows batch‐script syntax and keywords (e.g. commands like REM, SET, ECHO, CALL, pushd/popd, @, etc.).

    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
     Shoe
    -0.06
     farewell
    -0.06
    ideographic
    -0.06
    .Page
    -0.06
    」（
    -0.06
     "".
    -0.06
     /^\
    -0.06
    .TEXT
    -0.06
    pygame
    -0.06
    .Constant
    -0.06
    POSITIVE LOGITS
    cult
    0.07
     Comics
    0.07
    pectral
    0.06
     Turbo
    0.06
    чий
    0.06
    ա�
    0.06
    _fl
    0.06
    碎
    0.06
    [u
    0.06
     gramm
    0.06
    Activations Density 0.005%

    No Known Activations