© 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. 91250
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    np_max-act · gemini-2.0-flash

    references to vascular function and responses related to nitric oxide in the context of hypertension and endothelial health.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of cholinergic agonists or acetylcholine-induced responses.

    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
    スマ
    -0.07
     zm
    -0.07
    ディース
    -0.07
     дней
    -0.06
    したら
    -0.06
    кових
    -0.06
     Singh
    -0.06
     Joy
    -0.06
     lance
    -0.06
    .isNotBlank
    -0.06
    POSITIVE LOGITS
     neob
    0.07
     advant
    0.06
    .minecraftforge
    0.06
    енти
    0.06
    ateway
    0.06
    invite
    0.06
    .expires
    0.06
     handleClick
    0.06
     گزارش
    0.06
     wounds
    0.06
    Activations Density 0.039%

    No Known Activations