© 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. 7839
    Prev
    Next
    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash

    This neuron detects document section headings, especially the “Case Report” title and its surrounding structural markers.

    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
     وارد
    -0.07
     Operand
    -0.07
    _empty
    -0.06
    チ
    -0.06
     Junk
    -0.06
    ustom
    -0.06
    lectric
    -0.06
    tod
    -0.06
    ('/:
    -0.06
    _nsec
    -0.06
    POSITIVE LOGITS
     showcasing
    0.06
     appreciation
    0.06
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.06
     intricate
    0.06
     current
    0.06
     Arabs
    0.06
     enforce
    0.06
     yatırım
    0.06
     når
    0.06
    ENTIC
    0.06
    Activations Density 0.006%

    No Known Activations