© 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. 51284
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    the neuron detects scientific/technical word stems and medical/research terminology (i.e., tokens that are parts of technical or domain-specific words).

    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
     scratched
    -0.06
     leaning
    -0.06
    Lee
    -0.06
    niž
    -0.06
     horrors
    -0.06
     multic
    -0.06
    Pour
    -0.06
    Ş
    -0.06
    �
    -0.06
     ttl
    -0.06
    POSITIVE LOGITS
    ∧
    0.07
    erase
    0.07
     oggi
    0.07
     ramen
    0.06
     otur
    0.06
     Tempo
    0.06
     کنترل
    0.06
     konnte
    0.06
     Fiat
    0.06
    .Phone
    0.06
    Activations Density 0.339%

    No Known Activations