© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108115
    Prev
    Next
    INDEX
    Explanations

    terms related to optics and optical technologies

    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
    ilet
    -0.07
    arest
    -0.06
    pa
    -0.06
    /de
    -0.06
    lan
    -0.06
    est
    -0.06
    IPS
    -0.06
    anter
    -0.06
    cheduler
    -0.06
    åŃĿ
    -0.06
    POSITIVE LOGITS
    /opt
    0.10
    eza
    0.07
    rippling
    0.07
    -intensive
    0.07
    pheric
    0.07
    tif
    0.07
    uke
    0.07
    tom
    0.07
    /video
    0.07
    aos
    0.07
    Activations Density 0.004%

    No Known Activations