© 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. 79832
    Prev
    Next
    INDEX
    Explanations

    occurrences of substantial focus or impact in various contexts

    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
     recent
    -0.10
     recently
    -0.09
     upcoming
    -0.08
    recent
    -0.08
     currently
    -0.07
     soon
    -0.07
     future
    -0.07
     next
    -0.07
     earlier
    -0.07
    soon
    -0.07
    POSITIVE LOGITS
    .Today
    0.10
    umes
    0.08
    ä¸Ģ缴
    0.08
     olmuÅŁtur
    0.08
    tember
    0.08
     Blanch
    0.07
     بÙĪدÙĩ
    0.07
    ÄĽtÅ¡
    0.07
    ÄĽn
    0.07
    secutive
    0.07
    Activations Density 0.089%

    No Known Activations