© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78232
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical specifications

    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
    oi
    -0.08
    edy
    -0.07
    emsp
    -0.06
    tember
    -0.06
    RunLoop
    -0.06
    ourd
    -0.06
    å·Ŀ
    -0.06
     Voj
    -0.06
    оÑı
    -0.06
     Branch
    -0.06
    POSITIVE LOGITS
     incl
    0.07
    incl
    0.06
    aley
    0.06
    ittle
    0.06
    SEP
    0.06
    ãĥ¼ãĤº
    0.06
    ær
    0.06
     ÑĢанÑĮ
    0.06
     Snape
    0.06
    éĸ¢ä¿Ĥ
    0.06
    Activations Density 0.003%

    No Known Activations