© 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. 15-LLAMASCOPE-RES-131K
    11. 87009
    Prev
    Next
    INDEX
    Explanations

    elements related to improving processes and functionality in systems or products

    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
    OLON
    -0.07
    eldom
    -0.07
    ego
    -0.07
     詳細
    -0.07
    amy
    -0.07
    ainen
    -0.07
    cntl
    -0.07
     Comple
    -0.06
    лÑıн
    -0.06
    contrast
    -0.06
    POSITIVE LOGITS
     without
    0.15
     yet
    0.14
    without
    0.13
     WITHOUT
    0.13
    Without
    0.12
     while
    0.12
     Without
    0.12
     but
    0.11
     ohne
    0.11
    while
    0.11
    Activations Density 0.205%

    No Known Activations