© 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. 29879
    Prev
    Next
    INDEX
    Explanations

    code or equations

    np_max-act · gemini-2.0-flash

    This neuron activates on LaTeX table/array column‐alignment specifiers (e.g. the “r”, “l”, “rr”, “ll” in \begin{array}{…} or tabular environments).

    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
    亭
    -0.08
    >Status
    -0.07
     μας
    -0.07
     Gwen
    -0.07
    θα
    -0.06
    talk
    -0.06
    ована
    -0.06
     uống
    -0.06
    Muslim
    -0.06
    ologist
    -0.06
    POSITIVE LOGITS
    (cv
    0.07
     Coupe
    0.07
    _ROUND
    0.07
    -vertical
    0.06
     guit
    0.06
    ,proto
    0.06
    _dll
    0.06
    ニニニニ
    0.06
     directional
    0.06
     patiently
    0.06
    Activations Density 0.001%

    No Known Activations