© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85722
    Prev
    Next
    INDEX
    Explanations

    warm

    np_max-act · gemini-2.0-flash

    This neuron fires on words describing temperature- or liquid-based remedies (e.g. warm, cold, ice, water) in treatment instructions.

    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
    escription
    -0.07
     piss
    -0.07
    ски
    -0.06
     agua
    -0.06
     articulated
    -0.06
     Sally
    -0.06
     kickoff
    -0.06
     tuna
    -0.06
    anvas
    -0.06
    utorial
    -0.06
    POSITIVE LOGITS
     ̄`
    0.08
     amigo
    0.07
    797
    0.07
     있도록
    0.06
    (Stream
    0.06
     встанов
    0.06
     아니라
    0.06
    EI
    0.06
     مدل
    0.06
    .bean
    0.06
    Activations Density 0.004%

    No Known Activations