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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30995
    Prev
    Next
    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—specifically multi‐digit substrings of the answers in the arithmetic/base‐conversion problems.

    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
     ماند
    -0.06
     lineage
    -0.06
     代
    -0.06
    بوب
    -0.06
    ğitim
    -0.06
     zosta
    -0.06
    わせ
    -0.06
    099
    -0.06
    seealso
    -0.06
     Ş
    -0.06
    POSITIVE LOGITS
    organic
    0.07
    IP
    0.07
     Ark
    0.07
    Nich
    0.07
     marriage
    0.07
    portion
    0.06
     NAV
    0.06
     peasant
    0.06
    διο
    0.06
     navy
    0.06
    Activations Density 0.007%

    No Known Activations