© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60832
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to quantum mechanics and field theory

    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
    521
    -0.06
     Knot
    -0.06
    667
    -0.06
    -binary
    -0.06
    è°·
    -0.06
     Dominion
    -0.06
    amu
    -0.06
     ÑĤеÑĢÑĢиÑĤоÑĢ
    -0.06
     Interval
    -0.06
     Integer
    -0.06
    POSITIVE LOGITS
     expectation
    0.08
    wik
    0.07
    çļ
    0.07
     expectations
    0.07
    igt
    0.06
     startPosition
    0.06
     Dix
    0.06
    ivet
    0.06
     bras
    0.06
    inger
    0.06
    Activations Density 0.282%

    No Known Activations