© 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. 81357
    Prev
    Next
    INDEX
    Explanations

    references to rankings or positions

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

    Content related to digital information architecture including article titles, URLs, metadata, citations, and technical references that typically appear in online documentation or content management systems.

    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
     mastur
    -0.12
    ,âĢ¦↵↵
    -0.12
     prostitu
    -0.11
     ört
    -0.11
     bát
    -0.10
    _________________↵↵
    -0.10
    ,...↵↵
    -0.10
    /stretch
    -0.10
    âĢ¦.↵↵
    -0.10
     tô
    -0.10
    POSITIVE LOGITS
    &apos
    0.09
    č
    0.07
    Âłs
    0.06
    Âłin
    0.06
    ...
    0.06
    Âł
    0.06
     ...
    0.06
    Âłd
    0.06
     diligent
    0.06
     individually
    0.06
    Activations Density 92.091%

    No Known Activations