© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68276
    Prev
    Next
    INDEX
    Explanations

    classifying carcinogens

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of major health or regulatory bodies (e.g. WHO/IARC) classifying chemicals or risks.

    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
     Speed
    -0.08
     detects
    -0.07
    Fac
    -0.06
     внимание
    -0.06
     McGu
    -0.06
    ascimento
    -0.06
     lur
    -0.06
     streamlined
    -0.06
    .Course
    -0.06
     dating
    -0.06
    POSITIVE LOGITS
    -byte
    0.07
    �
    0.07
    바이
    0.06
     první
    0.06
     boz
    0.06
    _fs
    0.06
     nạn
    0.06
    owania
    0.06
     primera
    0.06
     mother
    0.06
    Activations Density 0.020%

    No Known Activations