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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58008
    Prev
    Next
    INDEX
    Explanations

    coprime

    np_max-act · gemini-2.0-flash

    mathematical concepts and structures related to modular arithmetic and number theory.

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

    The neuron activates on mentions of numbers being “coprime” (relatively prime) or having no common factors.

    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
     synt
    -0.06
    Emoji
    -0.06
    _unique
    -0.06
     Bermuda
    -0.06
     passing
    -0.06
    raction
    -0.06
    actual
    -0.06
    icolor
    -0.06
     Isaiah
    -0.06
     rip
    -0.06
    POSITIVE LOGITS
    О
    0.07
    roti
    0.07
    �
    0.06
    WT
    0.06
    說
    0.06
     nez
    0.06
    AXB
    0.06
    configs
    0.06
     kk
    0.06
    CompatActivity
    0.06
    Activations Density 0.003%

    No Known Activations