© 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. 9-LLAMASCOPE-RES-131K
    11. 96842
    Prev
    Next
    INDEX
    Explanations

    references to medical databases and publications

    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
    [
    -0.06
    uu
    -0.06
    apan
    -0.06
    岡
    -0.06
    ing
    -0.06
    æµľ
    -0.06
     Gerard
    -0.05
    -fw
    -0.05
    eng
    -0.05
    anan
    -0.05
    POSITIVE LOGITS
    ilent
    0.07
    OLF
    0.07
    veloper
    0.07
    à¤Ĩर
    0.07
    \Collections
    0.07
    ModelProperty
    0.07
    .dsl
    0.07
    ħ
    0.07
    .gov
    0.07
    ensem
    0.07
    Activations Density 0.004%

    No Known Activations