© 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. 69778
    Prev
    Next
    INDEX
    Explanations

    references to institutions, locations, or specific historical facts

    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
     soon
    -0.09
     recently
    -0.09
     recent
    -0.08
     initially
    -0.08
     bisher
    -0.07
     originally
    -0.07
     lately
    -0.07
     then
    -0.07
     sooner
    -0.07
    ä¸Ģ缴
    -0.07
    POSITIVE LOGITS
     still
    0.12
     STILL
    0.12
    still
    0.12
     Still
    0.11
    Still
    0.11
    ä»į
    0.09
    adays
    0.09
     hâlâ
    0.08
     artık
    0.08
     vẫn
    0.08
    Activations Density 0.038%

    No Known Activations