Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128927
    Prev
    Next
    INDEX
    Explanations

    license information

    np_max-act · gemini-2.0-flash

    This neuron detects license‐and‐copyright header information lines (e.g., “license,” “information,” version numbers) in source-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
    Pipeline
    -0.07
     stressful
    -0.07
    ораль
    -0.07
     Souls
    -0.06
    _Method
    -0.06
    ネル
    -0.06
     stopwatch
    -0.06
     Recommended
    -0.06
    elsen
    -0.06
     polished
    -0.06
    POSITIVE LOGITS
    MASTER
    0.07
    )")
    0.06
     FileInfo
    0.06
    ٌ
    0.06
     step
    0.06
    [$_
    0.06
    edic
    0.06
    の中
    0.06
    .FILE
    0.06
     ">
    0.06
    Activations Density 0.002%

    No Known Activations