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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55347
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts, specifically functions and their characteristics

    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
    isÃŃ
    -0.08
    .toolbox
    -0.07
     Marketable
    -0.07
    alet
    -0.07
    wers
    -0.06
    Compiled
    -0.06
    \$
    -0.06
    çĵ
    -0.06
    vos
    -0.06
    ãĥ¼ãĥĨãĤ£
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.16
     like
    0.13
     ëĭ¤ìĿĮê³¼
    0.12
     ÅŁÃ¶yle
    0.12
    :↵
    0.11
     following
    0.10
     seguint
    0.10
     :↵
    0.10
     ÑģледÑĥÑİÑī
    0.09
     Like
    0.09
    Activations Density 0.247%

    No Known Activations