© 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. 38349
    Prev
    Next
    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash

    The neuron fires on C++ code identifiers and scoped names (e.g. class/method names with ::, templates, and CamelCase symbols).

    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
    advisor
    -0.07
     vọng
    -0.07
     reject
    -0.07
    .tell
    -0.07
     похож
    -0.07
    λος
    -0.06
    ูต
    -0.06
     Casting
    -0.06
     comprised
    -0.06
     cords
    -0.06
    POSITIVE LOGITS
     compressor
    0.07
     xhttp
    0.06
    \ActiveForm
    0.06
    loy
    0.06
     Colo
    0.06
     &#
    0.06
    )'
    0.06
    イン
    0.06
     Sy
    0.06
    をする
    0.06
    Activations Density 0.049%

    No Known Activations