© 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. 29237
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and licensing

    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
    weed
    -0.07
    unta
    -0.06
    forme
    -0.06
    ough
    -0.06
    ÃŃc
    -0.06
    idon
    -0.06
    ream
    -0.06
    aset
    -0.05
    ched
    -0.05
     dere
    -0.05
    POSITIVE LOGITS
    chedulers
    0.07
    .tcp
    0.07
    .gwt
    0.07
    Ïģη
    0.06
    .printStackTrace
    0.06
    .onViewCreated
    0.06
    Ease
    0.06
    bdb
    0.06
     Hose
    0.06
    ÙĪÙħÛĮ
    0.06
    Activations Density 0.001%

    No Known Activations