© 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. 29986
    Prev
    Next
    INDEX
    Explanations

    comprise

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the verb “comprise” (including its inflected forms like “comprises” and “comprising”).

    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
     当
    -0.07
     even
    -0.07
    on
    -0.07
    Ell
    -0.07
     fgets
    -0.07
     ink
    -0.07
     Anders
    -0.07
    enou
    -0.07
    acs
    -0.07
     aging
    -0.07
    POSITIVE LOGITS
     comprises
    0.12
     comprise
    0.10
     comprising
    0.10
     comprehend
    0.08
     справ
    0.07
     boasts
    0.07
     comprised
    0.07
    -space
    0.07
     Fourth
    0.07
    rimp
    0.07
    Activations Density 0.005%

    No Known Activations