© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68669
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (years, volume and page numbers, reference ranges, patent and equation numbers) typically found in citations and technical references.

    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
    ('?
    -0.06
    directive
    -0.06
    >tagger
    -0.06
    -going
    -0.06
    634
    -0.06
    volatile
    -0.06
    crate
    -0.06
    _xpath
    -0.06
    |(↵
    -0.06
     moet
    -0.06
    POSITIVE LOGITS
    (UInt
    0.07
     circle
    0.07
    uyor
    0.06
    Turn
    0.06
     Were
    0.06
    щие
    0.06
    χεία
    0.06
     oper
    0.06
     Silent
    0.06
     Blizzard
    0.06
    Activations Density 0.003%

    No Known Activations