© 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. 87876
    Prev
    Next
    INDEX
    Explanations

    references to official documentation and bibliographic information

    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
    rego
    -0.06
    lea
    -0.06
    emu
    -0.06
    alin
    -0.06
    nds
    -0.06
    wend
    -0.06
    ragments
    -0.06
     moder
    -0.06
    .opend
    -0.06
    wen
    -0.06
    POSITIVE LOGITS
    Library
    0.08
     Library
    0.08
     libr
    0.08
    UCT
    0.07
     libraries
    0.07
    libraries
    0.07
     Libraries
    0.07
     library
    0.07
     Jacket
    0.07
     Jackets
    0.07
    Activations Density 0.003%

    No Known Activations