© 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. 81593
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to computer graphics and vertex shader programming

    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
    ilter
    -0.07
    eki
    -0.07
    lund
    -0.07
    äºľ
    -0.07
    lacak
    -0.06
     Bos
    -0.06
    ì¸
    -0.06
     forKey
    -0.06
    =sys
    -0.06
    kovi
    -0.06
    POSITIVE LOGITS
     corresponding
    0.09
     correspond
    0.08
    ê°ģ
    0.08
     each
    0.07
     accompanying
    0.06
     correspondent
    0.06
    amat
    0.06
    doch
    0.06
    umbo
    0.06
     labels
    0.06
    Activations Density 0.079%

    No Known Activations