© 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 EvalsExportsinterp-engineNEWAPI 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. 102718
    Prev
    Next
    INDEX
    Explanations

    Curly brace

    np_max-act · gemini-2.0-flash

    This neuron never activates (i.e. it does not detect any token pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    elements related to mathematical concepts and formal definitions in the context of calculus and physics.

    oai_token-act-pair · gpt-4o-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
    foobar
    -0.07
    inition
    -0.07
    CCA
    -0.07
     Buffy
    -0.06
    �택
    -0.06
    Markdown
    -0.06
    -aware
    -0.06
     cor
    -0.06
    薦
    -0.06
     наук
    -0.06
    POSITIVE LOGITS
     sut
    0.06
    (jq
    0.06
     Shuttle
    0.06
    Transmission
    0.06
    _loop
    0.06
    ΙΟ
    0.06
    .bn
    0.06
    ทำให
    0.06
    にか
    0.06
     interested
    0.06
    Activations Density 0.011%

    No Known Activations