© 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. 38189
    Prev
    Next
    INDEX
    Explanations

    processing of substances

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing experimental protocol actions or lab‐method steps (e.g., “sheared,” “extracted,” “prepared,” “size‐selected”).

    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
    Threshold
    -0.08
    included
    -0.07
     unearth
    -0.07
    .getMax
    -0.07
    为空
    -0.07
     فال
    -0.06
     dál
    -0.06
    _dest
    -0.06
    Tex
    -0.06
    After
    -0.06
    POSITIVE LOGITS
    rats
    0.07
     {?>↵
    0.07
    "?↵↵
    0.07
     Eig
    0.07
    ۱۰
    0.07
     Микола
    0.06
    ันท
    0.06
     unab
    0.06
     mainBundle
    0.06
     дані
    0.06
    Activations Density 0.057%

    No Known Activations