© 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 EvalsExportsinterp-engineNEWAPI 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. 5242
    Prev
    Next
    INDEX
    Explanations

    references to new species, methods, materials, and treatments, specifically in scientific contexts

    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
    .IContainer
    -0.08
     destinationViewController
    -0.07
     fitte
    -0.07
    vrier
    -0.07
    _except
    -0.06
    æģ
    -0.06
    gang
    -0.06
    dech
    -0.06
    linger
    -0.06
    von
    -0.06
    POSITIVE LOGITS
     discovery
    0.08
     phenomenon
    0.07
     discovered
    0.07
     insights
    0.07
     previously
    0.07
    ãĤ¸
    0.07
    ج
    0.06
     unique
    0.06
     phenomena
    0.06
     addition
    0.06
    Activations Density 0.024%

    No Known Activations