Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85879
    Prev
    Next
    INDEX
    Explanations

    code processing

    np_max-act · gemini-2.0-flash

    The neuron fires on the Python “def” keyword—that is, it detects function‐definition lines in Python 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
    >List
    -0.08
     trim
    -0.07
    -shirt
    -0.07
    itor
    -0.06
     EXPECT
    -0.06
     tat
    -0.06
     avez
    -0.06
    =false
    -0.06
    -containing
    -0.06
     warn
    -0.06
    POSITIVE LOGITS
    ;");↵
    0.07
    udio
    0.07
    lected
    0.07
    าง
    0.06
    مد
    0.06
    реди
    0.06
    .compiler
    0.06
    िव
    0.06
    авис
    0.06
    _registry
    0.06
    Activations Density 0.237%

    No Known Activations