© 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. 61669
    Prev
    Next
    INDEX
    Explanations

    articles and nouns that describe items or experiences

    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
    æĹ¢
    -0.10
    ساÙĨÛĮ
    -0.08
     både
    -0.07
    /Internal
    -0.07
     Dollars
    -0.07
     alıp
    -0.06
    ocre
    -0.06
    668
    -0.06
     ãĢľ
    -0.06
    bourg
    -0.06
    POSITIVE LOGITS
     willingness
    0.10
     possibly
    0.09
    /or
    0.09
     chance
    0.09
    possibly
    0.08
     sense
    0.07
     ability
    0.07
     focus
    0.07
     possible
    0.07
     ke
    0.07
    Activations Density 0.048%

    No Known Activations