© 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. 68256
    Prev
    Next
    INDEX
    Explanations

    Against

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “Convention Against Torture” (often shown as CAT).

    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
    的声音
    -0.07
     boyut
    -0.06
     bitch
    -0.06
    elijke
    -0.06
     leap
    -0.06
    grp
    -0.06
    _the
    -0.06
     đồ
    -0.06
    (choice
    -0.06
    abeth
    -0.06
    POSITIVE LOGITS
     liner
    0.07
    ,),
    0.06
     kommt
    0.06
    ्त
    0.06
     leve
    0.06
     Grab
    0.06
     blankets
    0.06
     trimmed
    0.06
     providing
    0.06
    reator
    0.06
    Activations Density 0.001%

    No Known Activations