© 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. 15-RESID-POST-AA
    11. 99419
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    the neuron detects passages about safety, policy, or moderation issues and other sensitive content requiring rule-based handling.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mina
    -0.06
     diye
    -0.06
     Bast
    -0.06
    amine
    -0.06
    挂
    -0.06
     peptide
    -0.06
    -0.06
     Time
    -0.06
    яют
    -0.06
     Times
    -0.05
    POSITIVE LOGITS
    utivo
    0.07
    影
    0.07
    Conditional
    0.07
    $f
    0.06
    Bonjour
    0.06
     fraud
    0.06
     Bon
    0.06
    산업
    0.06
    홈
    0.06
    (let
    0.06
    Activations Density 0.022%

    No Known Activations