© 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. 55415
    Prev
    Next
    INDEX
    Explanations

    splitting or refactoring code

    np_max-act · gemini-2.0-flash

    This neuron fires on descriptive phrases advocating “smaller, more targeted (or cohesive) methods,” i.e. recommendations to break functionality into focused, narrowly scoped methods.

    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
     fro
    -0.07
     사이
    -0.07
    YST
    -0.06
    partials
    -0.06
    ::_
    -0.06
    appear
    -0.06
     rectangles
    -0.06
     callers
    -0.06
    efa
    -0.06
    POSITIVE LOGITS
     algún
    0.07
     Walton
    0.06
     東
    0.06
     asla
    0.06
    Lab
    0.06
    -таки
    0.06
     FRE
    0.06
    零
    0.06
     concrete
    0.06
    _empresa
    0.06
    Activations Density 0.021%

    No Known Activations