© 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. 15-RESID-POST-AA
    11. 124284
    Prev
    Next
    INDEX
    Explanations

    protagonist

    np_max-act · gemini-2.0-flash

    Mentions or labels that identify a character as the protagonist (main/mainly character).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hoover
    -0.07
     nums
    -0.06
    服務
    -0.06
    _TRI
    -0.06
    енням
    -0.06
    &quot
    -0.06
    	direction
    -0.06
     briefing
    -0.06
    .HTTP
    -0.06
    ormap
    -0.06
    POSITIVE LOGITS
    (ArrayList
    0.07
     Made
    0.07
    ↵↵↵↵↵↵
    0.07
     |:
    0.07
     результате
    0.07
    �
    0.07
     Provided
    0.07
     heroine
    0.07
     jejichž
    0.07
    .Shared
    0.07
    Activations Density 0.015%

    No Known Activations