© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7945
    Prev
    Next
    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash

    The neuron primarily detects mentions of named individuals in legal contexts—especially lawyers, prosecutors, and other courtroom figures.

    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
     vulgar
    -0.07
     decree
    -0.07
    _INSTALL
    -0.07
     Warp
    -0.07
    .DB
    -0.06
     compassion
    -0.06
    니아
    -0.06
    ικών
    -0.06
     سرعت
    -0.06
     이야기
    -0.06
    POSITIVE LOGITS
     Representative
    0.07
    (dict
    0.07
    �
    0.07
    rání
    0.06
    ":[
    0.06
    živ
    0.06
    (tmp
    0.06
    utorials
    0.06
    (pi
    0.06
    )",↵
    0.06
    Activations Density 0.019%

    No Known Activations