© 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. 7-RESID-POST-AA
    11. 113059
    Prev
    Next
    INDEX
    Explanations

    Antibiotic

    np_max-act · gemini-2.0-flash

    Finds mentions of a specific nitroimidazole-class antibiotic (references to that drug in medical contexts).

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gand
    -0.06
    ニﾆ
    -0.06
    (Common
    -0.06
     индивиду
    -0.06
     hybrids
    -0.06
     Pis
    -0.06
    -static
    -0.06
     إلي
    -0.06
     vale
    -0.06
    (credentials
    -0.06
    POSITIVE LOGITS
    _json
    0.09
    Method
    0.06
     Asheville
    0.06
     Against
    0.06
    ेशन
    0.06
    ospital
    0.06
    요일
    0.06
    iming
    0.06
    acea
    0.06
    Quest
    0.06
    Activations Density 0.002%

    No Known Activations