© 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. 39024
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    elements related to software licensing and build configuration within a codebase.

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

    The neuron fires on library names and build‐system flags in code, identifying tokens like compiler/linker options and library identifiers.

    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
    ाण
    -0.07
    .zip
    -0.07
     requestData
    -0.06
    $stmt
    -0.06
    :update
    -0.06
     fastball
    -0.06
    _capacity
    -0.06
     disgusted
    -0.06
     flair
    -0.06
    .TabControl
    -0.06
    POSITIVE LOGITS
     terra
    0.07
    ağın
    0.07
     Ende
    0.06
     tä
    0.06
    fov
    0.06
     ah
    0.06
    (strip
    0.06
    Türkiye
    0.06
    !=
    0.06
    ,-
    0.06
    Activations Density 0.031%

    No Known Activations