© 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. 15-LLAMASCOPE-RES-131K
    11. 87942
    Prev
    Next
    INDEX
    Explanations

    large quantities of data related to businesses, consumers, and professionals

    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
    927
    -0.07
    οι
    -0.07
    orer
    -0.07
    antz
    -0.06
    íĦ¸
    -0.06
    SORT
    -0.06
    016
    -0.06
    078
    -0.06
    .Encode
    -0.06
    725
    -0.06
    POSITIVE LOGITS
     company
    0.07
    одо
    0.07
     Achilles
    0.06
     haystack
    0.06
    unker
    0.06
    werk
    0.06
    ocio
    0.06
    moz
    0.06
    ONUS
    0.06
    ursal
    0.06
    Activations Density 0.009%

    No Known Activations