© 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. 87866
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements related to performance and averages

    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
     acomp
    -0.07
    æ¯Ķä¾ĭ
    -0.07
    bcm
    -0.06
    ãĤ¿ãĥ³
    -0.06
     mul
    -0.06
     caller
    -0.06
    ãĥ¼ãĥĢ
    -0.06
     infinit
    -0.06
    оÑĢи
    -0.06
    caller
    -0.06
    POSITIVE LOGITS
     sectional
    0.08
     maximum
    0.08
    æľĢé«ĺ
    0.07
    imd
    0.07
    .max
    0.06
     bench
    0.06
    rete
    0.06
    maximum
    0.06
     hog
    0.06
    æı¡
    0.06
    Activations Density 0.060%

    No Known Activations