© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash

    This neuron detects methodological reporting details in systematic reviews, especially literature‐search elements such as database names, date ranges, and search timing.

    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
     rims
    -0.06
     ')
    -0.06
    .asm
    -0.06
     hotline
    -0.06
     redirect
    -0.06
    oyer
    -0.06
     oneself
    -0.06
    mpar
    -0.06
     Americ
    -0.06
     Ralph
    -0.06
    POSITIVE LOGITS
    ulative
    0.06
     дозвол
    0.06
    λω
    0.06
     SYNC
    0.06
    urgery
    0.06
    .getCount
    0.06
     Appropri
    0.06
    았다
    0.06
    _step
    0.06
    .ix
    0.06
    Activations Density 0.011%

    No Known Activations