© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 101358
    Prev
    Next
    INDEX
    Explanations

    frequent

    np_max-act · gemini-2.0-flash

    medical terminology and conditions related to children's health.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    the neuron responds to mentions of numerical counts, statistics, or quantitative information (numbers and related terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Sent
    -0.07
     Phó
    -0.06
     lạ
    -0.06
     Founder
    -0.06
     valida
    -0.06
     conformity
    -0.06
     WIFI
    -0.06
     Pant
    -0.06
    TX
    -0.06
    existent
    -0.06
    POSITIVE LOGITS
     veil
    0.07
    SetBranch
    0.07
     eat
    0.06
    ?>↵↵
    0.06
     believe
    0.06
    Imagine
    0.06
     să
    0.06
    _die
    0.06
     stake
    0.06
    MouseDown
    0.06
    Activations Density 0.975%

    No Known Activations