© 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 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. 56806
    Prev
    Next
    INDEX
    Explanations

    Divisibility

    np_max-act · gemini-2.0-flash

    The neuron detects the numerical values being tested (e.g. the candidate number in “Is X a factor …?” or “Does Y divide …?”) in math problem 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
     Most
    -0.07
     searches
    -0.07
     misunder
    -0.06
     pact
    -0.06
     таблиц
    -0.06
     PDT
    -0.06
     communic
    -0.06
    114
    -0.06
     FIL
    -0.06
    348
    -0.06
    POSITIVE LOGITS
    entlich
    0.07
    lerimiz
    0.06
     влас
    0.06
    (Base
    0.06
    暗
    0.06
    去了
    0.06
     distancing
    0.06
     зв
    0.05
    _draw
    0.05
    Architecture
    0.05
    Activations Density 0.004%

    No Known Activations