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. 40431
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    The neuron fires on JSON-style object property names and delimiters, marking the structure of config or package files.

    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
     İki
    -0.08
    VI
    -0.07
    kt
    -0.07
     Hiện
    -0.06
     satire
    -0.06
     Vincent
    -0.06
     Pets
    -0.06
     cJSON
    -0.06
     salsa
    -0.06
     Defensive
    -0.06
    POSITIVE LOGITS
    он
    0.08
    0
    0.07
    ou
    0.07
    ,或
    0.07
      ↵    ↵
    0.07
    erox
    0.07
    .O
    0.07
    PD
    0.07
    /portfolio
    0.06
    mand
    0.06
    Activations Density 0.018%

    No Known Activations