© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17031
    Prev
    Next
    INDEX
    Explanations

    technical language and programming-related terms

    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
     eoq
    -0.09
     Angiospermae
    -0.09
    #
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
     nhau
    -0.08
    #ad
    -0.07
    /goto
    -0.07
    iв
    -0.07
    ÃĹ↵↵
    -0.07
    /fw
    -0.07
    POSITIVE LOGITS
     =
    0.09
    andy
    0.06
    O
    0.06
     Kan
    0.06
     =↵
    0.06
    edor
    0.05
     temp
    0.05
     Kür
    0.05
    erot
    0.05
    A
    0.05
    Activations Density 0.027%

    No Known Activations