© 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. 125655
    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
    κÏħ
    -0.07
    razier
    -0.07
    enthal
    -0.07
     dsp
    -0.07
    aptive
    -0.07
    à¸Ħว
    -0.07
    иÑģк
    -0.07
    azar
    -0.07
    зв
    -0.07
    Ïģε
    -0.07
    POSITIVE LOGITS
     ramifications
    0.06
    itur
    0.06
     spiral
    0.06
     Doctor
    0.06
     next
    0.06
     node
    0.06
    uzzi
    0.05
     Spiral
    0.05
    orida
    0.05
     tou
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.