© 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. 68938
    Prev
    Next
    INDEX
    Explanations

    Code/configuration snippets

    np_max-act · gemini-2.0-flash

    The neuron primarily detects code tokens involved in function or method invocations (especially the parentheses in call expressions).

    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
    _macros
    -0.06
    controller
    -0.06
    스타
    -0.06
     Ster
    -0.06
    Cele
    -0.06
    reen
    -0.06
    REEN
    -0.06
    >In
    -0.06
    _appro
    -0.06
    POSITIVE LOGITS
     чет
    0.07
     cs
    0.07
    .getPosition
    0.06
    _axes
    0.06
     مشار
    0.06
    modx
    0.06
     gek
    0.06
     cgi
    0.06
     پا
    0.06
    係
    0.06
    Activations Density 0.067%

    No Known Activations