© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80035
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Vassili" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estroy
    -0.08
    aiser
    -0.08
    جاÙħ
    -0.08
    коÑĤ
    -0.08
    ycastle
    -0.08
    ¦¬
    -0.08
    NAMESPACE
    -0.07
    anks
    -0.07
    è·
    -0.07
    isman
    -0.07
    POSITIVE LOGITS
    à¥įतव
    0.07
    quez
    0.06
    351
    0.06
    undle
    0.06
    gard
    0.06
    co
    0.06
    UGH
    0.06
    cul
    0.05
     Brewers
    0.05
    ques
    0.05
    Activations Density 0.009%

    No Known Activations