© 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. 61404
    Prev
    Next
    INDEX
    Explanations

    references to cosmic and astronomical concepts

    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
    ãĤ¯ãĤ»
    -0.07
    ализи
    -0.07
    vsp
    -0.07
    .Sdk
    -0.06
     land
    -0.06
     frontal
    -0.06
    qv
    -0.06
     satellites
    -0.06
     ÏĢά
    -0.06
    terra
    -0.06
    POSITIVE LOGITS
     gal
    0.07
    gal
    0.07
    å·Ŀ
    0.06
    .od
    0.06
     stars
    0.06
     αÏĢ
    0.06
     Stars
    0.06
    åļ
    0.06
    .dtd
    0.06
     universe
    0.06
    Activations Density 0.006%

    No Known Activations