© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96772
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ibrary
    -0.06
    annis
    -0.06
    ãģĹãģ®
    -0.06
    ereum
    -0.06
    bomb
    -0.06
    ephir
    -0.06
    ekl
    -0.06
    awei
    -0.06
    784
    -0.06
    rias
    -0.06
    POSITIVE LOGITS
    onet
    0.07
    .swt
    0.06
    YRO
    0.06
    ymology
    0.06
    iple
    0.06
    Å¡ka
    0.06
    panies
    0.06
    imler
    0.06
     Wing
    0.06
     Industries
    0.06
    Activations Density 0.077%

    No Known Activations