© 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. 73650
    Prev
    Next
    INDEX
    Explanations

    with, interactions

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of interacting with source code (e.g., “interactions,” “with,” “source,” “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
    沈
    -0.06
    cel
    -0.06
    rlen
    -0.06
    (tol
    -0.06
    \Foundation
    -0.06
    ерк
    -0.06
    골
    -0.06
    Blo
    -0.06
     chicken
    -0.06
     Zust
    -0.06
    POSITIVE LOGITS
    ити
    0.07
     Enrollment
    0.06
     Main
    0.06
     {
↵
↵
    0.06
    icana
    0.06
    كيب
    0.06
    ;',↵
    0.06
    Right
    0.06
     avantaj
    0.06
    일
    0.06
    Activations Density 0.001%

    No Known Activations