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. 130658
    Prev
    Next
    INDEX
    Explanations

    Past events

    np_max-act · gemini-2.0-flash

    This neuron detects numeric expressions and measurements (e.g., numbers, dates, or decimal values) in the text.

    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
     AM
    -0.07
    .nasa
    -0.06
     公
    -0.06
     yielded
    -0.06
    να
    -0.06
    pictured
    -0.06
    avings
    -0.06
    под
    -0.06
    <num
    -0.06
    prov
    -0.06
    POSITIVE LOGITS
    ]*
    0.07
    ation
    0.07
    =*
    0.07
     )*
    0.07
     Dank
    0.06
    ()*
    0.06
    Bu
    0.06
    /.
    0.06
    touches
    0.06
     chính
    0.06
    Activations Density 0.113%

    No Known Activations