© 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. 7844
    Prev
    Next
    INDEX
    Explanations

    title, label, text

    np_max-act · gemini-2.0-flash

    The neuron fires on code tokens that name or supply user‐facing UI properties (like title, text, label, icon, Content, etc.) in declarations and attributes.

    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
    ≤
    -0.07
     interactive
    -0.06
     Seconds
    -0.06
    qué
    -0.06
     Huss
    -0.06
    _comm
    -0.06
     Bik
    -0.06
    odes
    -0.06
     wer
    -0.06
     mouseX
    -0.06
    POSITIVE LOGITS
     oracle
    0.07
    Holy
    0.07
    getRoot
    0.06
     دام
    0.06
    _MODULE
    0.06
     Maybe
    0.06
     painful
    0.06
    �에
    0.06
     지방
    0.06
     вспом
    0.06
    Activations Density 0.011%

    No Known Activations