© 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. 37930
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    This neuron detects comparative and superlative degree terms—words that signal a comparison (e.g. “more,” “faster,” “greater,” “slower,” etc.).

    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
    combine
    -0.07
     ink
    -0.07
     mirror
    -0.07
     Finch
    -0.07
    EventData
    -0.06
     klíč
    -0.06
     akşam
    -0.06
    っく
    -0.06
    /md
    -0.06
    png
    -0.06
    POSITIVE LOGITS
    gres
    0.08
    ،↵
    0.07
     Canterbury
    0.07
     يوليو
    0.06
    />.↵↵
    0.06
     krat
    0.06
     perce
    0.06
    sembl
    0.06
     корпус
    0.06
     gore
    0.06
    Activations Density 0.078%

    No Known Activations