© 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. 89738
    Prev
    Next
    INDEX
    Explanations

    js

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting occurrences of the string “js” (as in file extensions or module format names like “commonjs”).

    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
    овані
    -0.07
    开展
    -0.07
     Bashar
    -0.07
     предус
    -0.06
    以来
    -0.06
    制度
    -0.06
     Lös
    -0.06
     BehaviorSubject
    -0.06
    Perfil
    -0.06
    kemiz
    -0.06
    POSITIVE LOGITS
    mq
    0.07
    OCR
    0.06
    852
    0.06
     vote
    0.06
    .CH
    0.06
    <a
    0.06
    級
    0.06
    cılık
    0.06
    OCK
    0.06
    _STRUCTURE
    0.06
    Activations Density 0.005%

    No Known Activations