© 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. 78420
    Prev
    Next
    INDEX
    Explanations

    concepts related to molecular biology and advanced materials science

    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
     âĢª
    -0.08
     nues
    -0.07
    apel
    -0.07
     odbor
    -0.07
    æĸ¹
    -0.07
    forme
    -0.07
    ayo
    -0.07
    åŁ
    -0.07
    <<<
    -0.07
     SVC
    -0.07
    POSITIVE LOGITS
     various
    0.07
     applications
    0.06
     latest
    0.06
    omes
    0.06
     prefixed
    0.06
     Chap
    0.06
    /latest
    0.06
    -based
    0.06
     worldwide
    0.06
    jom
    0.05
    Activations Density 0.005%

    No Known Activations