© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60150
    Prev
    Next
    INDEX
    Explanations

    terms related to documents, data formats, and data structures in software and databases

    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
     hol
    -0.06
     cra
    -0.06
     dec
    -0.06
    /archive
    -0.06
     finally
    -0.06
    ut
    -0.06
     accounted
    -0.05
     already
    -0.05
     wil
    -0.05
     را
    -0.05
    POSITIVE LOGITS
    rather
    0.10
     rather
    0.09
    å½¢å¼ı
    0.08
    ois
    0.08
    wart
    0.07
    766
    0.07
    ouro
    0.07
    niž
    0.07
     Rather
    0.07
     format
    0.07
    Activations Density 0.044%

    No Known Activations