© 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 EvalsExportsinterp-engineNEWAPI 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. 27456
    Prev
    Next
    INDEX
    Explanations

    во

    np_max-act · gemini-2.0-flash

    the Russian temporal phrase "во время" (indicating "during/while").

    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
     picked
    -0.07
     scattering
    -0.07
     Matching
    -0.07
    appro
    -0.07
     tích
    -0.06
    ר
    -0.06
    elden
    -0.06
    觀
    -0.06
     matching
    -0.06
     wallets
    -0.06
    POSITIVE LOGITS
     во
    0.09
    онт
    0.07
    	        ↵
    0.07
     Во
    0.07
    Во
    0.07
    (hObject
    0.06
     않고
    0.06
    (qu
    0.06
    (arguments
    0.06
     verb
    0.06
    Activations Density 0.002%

    No Known Activations