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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 127601
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron activates on personal names (especially names of judges, parties, or attorneys) in legal-case headings and text.

    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
    @NoArgsConstructor
    -0.07
    核
    -0.06
     Sessions
    -0.06
     water
    -0.06
     systematic
    -0.06
    _UP
    -0.06
    -Semit
    -0.06
     jezd
    -0.06
    .touches
    -0.06
    ارت
    -0.06
    POSITIVE LOGITS
     nodded
    0.06
    chází
    0.06
    았
    0.06
    іє
    0.06
     něco
    0.06
    cular
    0.06
    엇
    0.06
     vš
    0.06
    (FILE
    0.06
     zpět
    0.06
    Activations Density 0.006%

    No Known Activations