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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41500
    Prev
    Next
    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of (various forms of) the word “sort,” i.e. tokens related to sorting.

    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
    undo
    -0.07
     pian
    -0.06
    categorie
    -0.06
    abra
    -0.06
    _FM
    -0.06
    MOOTH
    -0.06
    vester
    -0.06
     venda
    -0.06
     landsc
    -0.06
     eder
    -0.06
    POSITIVE LOGITS
    Improved
    0.07
     ofrec
    0.07
    {n
    0.07
     kö
    0.06
     verbally
    0.06
     Redskins
    0.06
    UEL
    0.06
     Druid
    0.06
     Preserve
    0.06
    .block
    0.06
    Activations Density 0.024%

    No Known Activations