© 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. 89723
    Prev
    Next
    INDEX
    Explanations

    issue

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the phrase “genuine issue” (as in “no genuine issue of material fact”) used in summary-judgment standards.

    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
    parer
    -0.07
    debit
    -0.06
     systematic
    -0.06
    씨
    -0.06
    ñas
    -0.06
    ﾞﾞ
    -0.06
    ocup
    -0.06
    tracted
    -0.06
    erokee
    -0.05
     backlash
    -0.05
    POSITIVE LOGITS
     hala
    0.07
     Mahm
    0.07
    월까지
    0.07
     ради
    0.06
     شما
    0.06
     tamamen
    0.06
     imkân
    0.06
    .checkBox
    0.06
    \<^
    0.06
    Otherwise
    0.06
    Activations Density 0.000%

    No Known Activations