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

    Neuronpedia

    Jacobian LensNEW
    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. 43175
    Prev
    Next
    INDEX
    Explanations

    Truth and deception

    np_max-act · gemini-2.0-flash

    Tokens that instruct or encourage inventing/making up information presented in a convincing, realistic way.

    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
    Push
    -0.07
    گل
    -0.07
    dling
    -0.06
    FTA
    -0.06
    _keyboard
    -0.06
    iêng
    -0.05
    -feature
    -0.05
     Portland
    -0.05
     حقوق
    -0.05
    كات
    -0.05
    POSITIVE LOGITS
     grayscale
    0.07
    	utils
    0.07
     Vys
    0.06
     radar
    0.06
     관리자
    0.06
     ;)
    0.06
    出售
    0.06
    _Admin
    0.06
     enroll
    0.06
    ivre
    0.06
    Activations Density 0.003%

    No Known Activations