© 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. 17253
    Prev
    Next
    INDEX
    Explanations

    references to people, music artists, languages, and numerical data

    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
     interf
    -0.07
    onis
    -0.07
    kees
    -0.07
    elib
    -0.07
    olib
    -0.07
    ικο
    -0.06
    ÙıÙĪÙĨ
    -0.06
    NAMESPACE
    -0.06
    eri
    -0.06
    ultiply
    -0.06
    POSITIVE LOGITS
    @nate
    0.07
     Lund
    0.07
    nodoc
    0.07
     XPAR
    0.07
    chandle
    0.07
    PathParam
    0.07
    atsby
    0.06
    ê¸ī
    0.06
    iedo
    0.06
    tabpanel
    0.06
    Activations Density 0.046%

    No Known Activations