© 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. 15-LLAMASCOPE-RES-131K
    11. 87693
    Prev
    Next
    INDEX
    Explanations

    important venues, systems, or mechanisms that are significant in specific 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
     various
    -0.07
     among
    -0.07
     any
    -0.06
     u
    -0.06
     exactly
    -0.06
     two
    -0.06
     specific
    -0.06
     respectively
    -0.06
    roids
    -0.06
     anymore
    -0.06
    POSITIVE LOGITS
     entire
    0.09
     Entire
    0.08
    LLL
    0.08
    æķ´ä¸ª
    0.07
    ozem
    0.07
     entirety
    0.07
     vÄįetnÄĽ
    0.07
    _except
    0.07
    Except
    0.07
    whole
    0.07
    Activations Density 0.050%

    No Known Activations