© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90903
    Prev
    Next
    INDEX
    Explanations

    "%"

    np_max-act · gemini-2.0-flash

    The neuron fires on Windows batch‐file keywords and syntax (e.g. “echo off,” “if …,” “set …,” “goto” etc.), i.e. control-flow and environment-variable commands in .bat scripts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    batch commands related to file management and execution on a Windows environment.

    oai_token-act-pair · gpt-4o-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
    aturday
    -0.07
     bapt
    -0.06
    檢
    -0.06
     concurrently
    -0.06
    _Float
    -0.06
     técn
    -0.06
     فهم
    -0.06
    _supported
    -0.06
    Contains
    -0.06
    eyond
    -0.06
    POSITIVE LOGITS
    approval
    0.07
    ous
    0.07
    Gear
    0.07
    enství
    0.07
    kal
    0.07
    /dir
    0.07
     alloy
    0.06
    _pll
    0.06
    ana
    0.06
    ("@
    0.06
    Activations Density 0.003%

    No Known Activations