© 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. 89361
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and serial configurations

    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
    /lg
    -0.09
    buz
    -0.09
    leton
    -0.07
    azzi
    -0.07
    igmoid
    -0.07
    .yang
    -0.07
    zzo
    -0.07
    ÑĢиÑı
    -0.07
    uby
    -0.06
    .Accessible
    -0.06
    POSITIVE LOGITS
     Seal
    0.06
    essel
    0.06
    TimeStamp
    0.05
    428
    0.05
     finally
    0.05
    ahoma
    0.05
     apl
    0.05
    583
    0.05
    į
    0.05
     Adv
    0.05
    Activations Density 0.004%

    No Known Activations