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. 86283
    Prev
    Next
    INDEX
    Explanations

    scientific ranges

    np_max-act · gemini-2.0-flash

    studies and methods related to dietary assessment and nutritional analysis.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating‐point numerical values (decimal numbers with several digits), as commonly used for statistical coefficients, p-values, or measurement results.

    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
     archivos
    -0.08
     diminishing
    -0.07
    etto
    -0.07
    axon
    -0.07
    321
    -0.06
     cardinal
    -0.06
    Settings
    -0.06
    erman
    -0.06
    amaged
    -0.06
     Rodriguez
    -0.06
    POSITIVE LOGITS
     пы
    0.07
    RGBO
    0.06
    );;↵
    0.06
     jMenuItem
    0.06
    停
    0.06
     Navbar
    0.06
     reverse
    0.06
    央
    0.06
     ПО
    0.06
     مث
    0.06
    Activations Density 0.020%

    No Known Activations