© 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. 27971
    Prev
    Next
    INDEX
    Explanations

    specific variables or mathematical symbols in a discussion about mathematical models and graphs

    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
    itol
    -0.06
    sink
    -0.06
    ariat
    -0.05
     coincidence
    -0.05
    andon
    -0.05
     fool
    -0.05
    ague
    -0.05
     hopefully
    -0.05
     occupancy
    -0.05
     competition
    -0.05
    POSITIVE LOGITS
    å±ŀäºİ
    0.10
    cheng
    0.09
     belongs
    0.08
     belong
    0.08
    ÑģÑıÑĤ
    0.08
    VEN
    0.08
     have
    0.08
     ÑıвлÑıеÑĤÑģÑı
    0.08
     are
    0.07
    ven
    0.07
    Activations Density 0.004%

    No Known Activations