© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80542
    Prev
    Next
    INDEX
    Explanations

    relationships and properties of waveguides and their modes in a scientific context

    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
    ston
    -0.06
     audible
    -0.06
    vre
    -0.06
     intellig
    -0.05
    igmat
    -0.05
    orget
    -0.05
     Clintons
    -0.05
     Unlock
    -0.05
    ForKey
    -0.05
     accepted
    -0.05
    POSITIVE LOGITS
    ä¸ĢåĮº
    0.08
    çļ
    0.07
    çĤİ
    0.07
    VOKE
    0.07
    á½·
    0.07
     Coupons
    0.07
    è¨Ń
    0.07
    èĬ¬
    0.07
    evin
    0.07
    RECT
    0.07
    Activations Density 0.034%

    No Known Activations