© 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. 15-LLAMASCOPE-RES-131K
    11. 26779
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating similarity or consistency

    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
     itself
    -0.08
    ange
    -0.08
     sám
    -0.07
    ilde
    -0.07
    lest
    -0.07
    otts
    -0.07
    istik
    -0.07
    æĺ¯ä¸ª
    -0.07
    stu
    -0.06
    .wik
    -0.06
    POSITIVE LOGITS
     themselves
    0.17
     yourselves
    0.09
     respectively
    0.08
     respective
    0.07
    -fw
    0.07
    áli
    0.07
    802
    0.07
    ató
    0.07
     nhau
    0.06
     catalyst
    0.06
    Activations Density 0.119%

    No Known Activations