© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 856
    Prev
    Next
    INDEX
    Explanations

    Code, arrays, image processing

    np_max-act · gemini-2.0-flash

    The neuron activates chiefly on Italian text—e.g. Italian words used in code comments or 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
    ेह
    -0.07
    >G
    -0.06
    (_
    -0.06
    .ap
    -0.06
    TH
    -0.06
     Gotham
    -0.06
    ompiler
    -0.06
    Milliseconds
    -0.06
    PV
    -0.06
    (h
    -0.06
    POSITIVE LOGITS
    ClickListener
    0.06
    +-+-
    0.06
    /frame
    0.06
    .tiles
    0.06
     توسعه
    0.06
    uckles
    0.06
     diplomacy
    0.06
     Nova
    0.06
     connectors
    0.06
    $name
    0.05
    Activations Density 0.052%

    No Known Activations