© 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. 6400
    Prev
    Next
    INDEX
    Explanations

    activity

    np_max-act · gemini-2.0-flash

    The neuron activates on biochemical enzyme terminology, especially enzyme names or mentions of enzyme‐catalyzed activity (e.g. words ending in “-ase” or “activity/catalyz­”).

    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
     Bak
    -0.07
    ΙΚ
    -0.06
     encompass
    -0.06
    fwrite
    -0.06
    ursion
    -0.06
    ighting
    -0.06
    LineColor
    -0.06
    وس
    -0.06
     sak
    -0.06
     Canton
    -0.06
    POSITIVE LOGITS
     जय
    0.07
    ['__
    0.07
     �
    0.06
    опри
    0.06
     úrov
    0.06
    ATIO
    0.06
     ARTICLE
    0.06
     вла
    0.06
     suppl
    0.06
    _ps
    0.06
    Activations Density 0.014%

    No Known Activations