© 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. 124832
    Prev
    Next
    INDEX
    Explanations

    computer vision technology

    np_max-act · gemini-2.0-flash

    technical terminology related to computer vision and image processing.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is a Cyrillic‐script detector—it activates on runs of Russian (Cyrillic) text.

    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
    Tes
    -0.06
    ora
    -0.06
     rolled
    -0.06
    Pass
    -0.06
    _transaction
    -0.06
    房间
    -0.06
    回来
    -0.06
     properly
    -0.06
     SKU
    -0.06
    Tro
    -0.05
    POSITIVE LOGITS
    )[-
    0.07
     messy
    0.07
     Ülke
    0.07
    infeld
    0.06
    τικής
    0.06
     Benjamin
    0.06
    -shadow
    0.06
    ственных
    0.06
    .coord
    0.06
    :')↵
    0.06
    Activations Density 0.096%

    No Known Activations