© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6935
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    This neuron detects document segmentation markers and headings that introduce or label parts (e.g., “Content 1:”, “Part 1”, “<start>” labels).

    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
     preorder
    -0.07
     compares
    -0.07
     CircularProgress
    -0.06
     metaphor
    -0.06
    ivated
    -0.06
     imped
    -0.06
    larımız
    -0.06
    asuring
    -0.06
    Um
    -0.06
    errmsg
    -0.06
    POSITIVE LOGITS
     рас
    0.08
     кор
    0.07
    娱乐
    0.06
     backlash
    0.06
    _scheduler
    0.06
     deception
    0.06
    MQ
    0.06
     foram
    0.06
    [--
    0.06
    もし
    0.06
    Activations Density 0.027%

    No Known Activations