© 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. 11-RESID-POST-AA
    11. 58648
    Prev
    Next
    INDEX
    Explanations

    раз

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on Russian word stems beginning with “раз-” (e.g. разоблачает, развиваться).

    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
    clinic
    -0.08
     Thai
    -0.08
     �
    -0.08
     BK
    -0.08
     Tik
    -0.07
    ęki
    -0.07
     นาง
    -0.07
     TK
    -0.07
    	CC
    -0.07
     خلق
    -0.07
    POSITIVE LOGITS
     раз
    0.12
     Раз
    0.08
    Раз
    0.08
    _ROUND
    0.07
     spread
    0.07
     roz
    0.07
     Roz
    0.07
     devised
    0.06
    다
    0.06
     рас
    0.06
    Activations Density 0.017%

    No Known Activations