© 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
    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. 125005
    Prev
    Next
    INDEX
    Explanations

    composite

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the word “composite,” i.e. it identifies mentions of composite numbers.

    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
     Screen
    -0.07
     Android
    -0.06
     screens
    -0.06
     factions
    -0.06
    iah
    -0.06
    electronics
    -0.06
    _xlim
    -0.06
     runners
    -0.06
    eah
    -0.06
     matcher
    -0.06
    POSITIVE LOGITS
    ظˆ
    0.06
    ตา
    0.06
     confirmPassword
    0.06
    change
    0.06
    を見る
    0.06
     supra
    0.06
    =======
    0.06
     visa
    0.06
     stif
    0.06
    .Syntax
    0.06
    Activations Density 0.002%

    No Known Activations