© 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. 124783
    Prev
    Next
    INDEX
    Explanations

    Ace

    np_max-act · gemini-2.0-flash

    This neuron detects uncommon or domain-specific tokens—specialized jargon, proper names, and rare words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    tokens that are rare or unusual subword pieces (uncommon words, names, or domain-specific/long morphemes).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     senate
    -0.07
     vượt
    -0.07
     بهبود
    -0.07
     decoder
    -0.06
     advises
    -0.06
     tier
    -0.06
    _vendor
    -0.06
     webpack
    -0.06
     millennium
    -0.06
    伦
    -0.06
    POSITIVE LOGITS
     oy
    0.06
     paced
    0.06
    LOY
    0.06
     tratamiento
    0.06
    _finish
    0.06
     یاد
    0.06
    iação
    0.05
    ovies
    0.05
    Resultado
    0.05
    _LINES
    0.05
    Activations Density 0.481%

    No Known Activations