© 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 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. 29414
    Prev
    Next
    INDEX
    Explanations

    keywords related to natural substances and their chemical properties

    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
     bid
    -0.07
     Grab
    -0.06
     run
    -0.06
     Millet
    -0.06
    æľĹ
    -0.06
    ach
    -0.06
     grab
    -0.06
     multim
    -0.06
    e
    -0.05
     summ
    -0.05
    POSITIVE LOGITS
    /WebAPI
    0.08
     ÙĨب
    0.07
    renom
    0.07
    åİħ
    0.07
     ÏĢαÏģά
    0.07
    æķ·
    0.07
     PROCUREMENT
    0.07
    APON
    0.07
    .nlm
    0.07
     å¿
    0.07
    Activations Density 0.065%

    No Known Activations