© 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. 62030
    Prev
    Next
    INDEX
    Explanations

    references to answers and answer-related tips in educational contexts

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

    Formatting markers and punctuation used in educational content, especially around question numbers, answer indicators, and section delimiters in quizzes and technical documents.

    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
    grave
    -0.06
    icion
    -0.06
    linger
    -0.06
    arus
    -0.06
    rust
    -0.06
    -peer
    -0.06
    UDENT
    -0.06
    bum
    -0.06
     con
    -0.06
     talk
    -0.05
    POSITIVE LOGITS
    orex
    0.07
    udit
    0.06
     pÅĻep
    0.06
     yem
    0.06
    encoded
    0.06
    untu
    0.06
    _________________↵↵
    0.06
    exampleInput
    0.06
    ynes
    0.06
     wz
    0.06
    Activations Density 0.006%

    No Known Activations