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. 84471
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on numeric literal tokens (especially floating-point constants) in 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
    mland
    -0.06
    ORITY
    -0.06
    scaling
    -0.06
    _tem
    -0.06
     galleries
    -0.06
    astery
    -0.06
     відповідно
    -0.06
    :::::::::::::
    -0.06
     EntityType
    -0.06
    술
    -0.06
    POSITIVE LOGITS
     fostering
    0.06
     another
    0.06
     Thanks
    0.06
     Target
    0.06
     waved
    0.06
    (temp
    0.06
     crushed
    0.06
    '));↵↵
    0.06
     sequ
    0.06
    ));↵↵↵
    0.06
    Activations Density 0.028%

    No Known Activations