© 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. 55467
    Prev
    Next
    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting license‐header references (e.g. “License,” “.txt,” “license”) in code file comments.

    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
    Cette
    -0.08
    Ố
    -0.07
    Larry
    -0.07
     Sullivan
    -0.06
    ullivan
    -0.06
     stamp
    -0.06
     broker
    -0.06
     stamps
    -0.06
    .tsv
    -0.06
     Shanghai
    -0.06
    POSITIVE LOGITS
     viewHolder
    0.06
     kidd
    0.06
    (mc
    0.06
     mitt
    0.06
    _rem
    0.06
    _Normal
    0.06
    zoom
    0.06
    追加
    0.06
     مقدم
    0.06
    unt
    0.06
    Activations Density 0.002%

    No Known Activations