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. 130638
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric expressions (cardinal numbers and digit‐based quantities).

    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
     Giấy
    -0.06
    branches
    -0.06
    激
    -0.06
     FileStream
    -0.06
    �
    -0.06
     constellation
    -0.06
    /export
    -0.06
    cano
    -0.06
    enery
    -0.06
    routing
    -0.06
    POSITIVE LOGITS
     WELL
    0.07
     destroy
    0.07
     Kişisel
    0.07
    πως
    0.07
     Pride
    0.07
     girls
    0.07
    olver
    0.06
     messy
    0.06
     Zeit
    0.06
    직
    0.06
    Activations Density 0.204%

    No Known Activations