© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 109500
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting numeric tokens (digits and related number‐words) in mathematical statements.

    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
    Merge
    -0.07
    PN
    -0.07
     cropped
    -0.07
    urst
    -0.06
    Prompt
    -0.06
    .members
    -0.06
    Altern
    -0.06
     burst
    -0.06
     rigs
    -0.06
     Catch
    -0.06
    POSITIVE LOGITS
    )-(
    0.07
    ่องเท
    0.07
     portraying
    0.06
     Intelligent
    0.06
    elage
    0.06
    κ
    0.06
    การเล
    0.06
     BLE
    0.06
     $_[
    0.06
    leur
    0.06
    Activations Density 0.011%

    No Known Activations