© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38520
    Prev
    Next
    INDEX
    Explanations

    research findings

    np_max-act · gemini-2.0-flash

    This neuron detects section-heading and discourse-marker phrases (e.g. “The present investigation,” “Results,” “Participants,” “Findings”) that structure scientific abstracts.

    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
     が
    -0.07
     závě
    -0.06
     Restaurant
    -0.06
     swingers
    -0.06
    phones
    -0.06
     plugged
    -0.06
    LECTION
    -0.06
     وات
    -0.06
    copy
    -0.06
     gamers
    -0.06
    POSITIVE LOGITS
     Пав
    0.07
    #af
    0.07
     Pompe
    0.07
    선거
    0.06
    ('/:
    0.06
     căn
    0.06
     undef
    0.06
     '.'
    0.06
    _ability
    0.06
     abusive
    0.06
    Activations Density 0.093%

    No Known Activations