© 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. 18150
    Prev
    Next
    INDEX
    Explanations

    terminology related to sampling techniques and methods

    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
    amat
    -0.07
    iggs
    -0.07
    ologue
    -0.06
    udem
    -0.06
    papers
    -0.06
    CY
    -0.06
    ieu
    -0.06
    ecc
    -0.06
     à¹Ĩ
    -0.06
    animate
    -0.06
    POSITIVE LOGITS
    plings
    0.09
    ting
    0.07
    rate
    0.07
    ra
    0.07
    vise
    0.07
    ishly
    0.07
    iazza
    0.07
    ian
    0.07
    GLenum
    0.07
    ToSelector
    0.07
    Activations Density 0.011%

    No Known Activations