© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124383
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    C++ code-related syntax and structure, specifically for defining classes and their methods.

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

    The neuron strongly activates on the question-mark token “?” when it’s used as the ternary/conditional operator in code.

    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
     Paz
    -0.07
    adows
    -0.06
    lasses
    -0.06
     Phen
    -0.06
    _other
    -0.06
    BSD
    -0.06
     <->
    -0.06
     heaters
    -0.06
    amentals
    -0.06
    amoto
    -0.06
    POSITIVE LOGITS
     margin
    0.07
    ?
    0.07
     tarihinde
    0.07
     gemacht
    0.07
     Gab
    0.07
    .INPUT
    0.07
     Sustainable
    0.06
     prefers
    0.06
    >%
    0.06
     typography
    0.06
    Activations Density 0.006%

    No Known Activations