© 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. 42828
    Prev
    Next
    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash

    commands and syntax related to batch scripting in Windows.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the Windows batch “for /f” loop construct in the script.

    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
    -tag
    -0.06
    .getData
    -0.06
    hyper
    -0.06
     haya
    -0.06
     黑
    -0.06
     lava
    -0.06
    abe
    -0.06
    _TR
    -0.06
     bothers
    -0.06
    _MED
    -0.06
    POSITIVE LOGITS
    yh
    0.07
    .getSource
    0.07
     #↵
    0.06
    .Cookie
    0.06
    .getBoolean
    0.06
    enticate
    0.06
    ií
    0.06
    .Documents
    0.06
    ्पत
    0.06
     xxxx
    0.06
    Activations Density 0.000%

    No Known Activations