© 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. 27801
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty

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

    End markers of mathematical expressions, questions, or statements that indicate a transition to a new speaker or section in academic or technical discourse.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Erg
    -0.07
     Rout
    -0.06
     Bust
    -0.06
    avad
    -0.06
     Shard
    -0.06
     Appendix
    -0.06
     footnote
    -0.06
    inton
    -0.06
    pers
    -0.05
    former
    -0.05
    POSITIVE LOGITS
    âng
    0.07
    eniable
    0.07
    æ¿ĥ
    0.07
    abei
    0.07
    ockets
    0.07
    -preview
    0.07
    üm
    0.07
    umbed
    0.06
    ãĥĻãĥ«
    0.06
    бÑĥдÑĮ
    0.06
    Activations Density 0.065%

    No Known Activations