© 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. 17-LLAMASCOPE-RES-131K
    11. 40414
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational structure and interactions

    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
    ï¸
    -0.07
    OLON
    -0.07
    isco
    -0.07
    asca
    -0.07
     dus
    -0.06
    ulos
    -0.06
    oras
    -0.06
    alla
    -0.06
     wherever
    -0.06
    ARAM
    -0.05
    POSITIVE LOGITS
     without
    0.10
    without
    0.09
     WITHOUT
    0.09
     Without
    0.09
     ohne
    0.08
    WITHOUT
    0.08
    pii
    0.08
    Without
    0.08
    _without
    0.07
     satisfactory
    0.07
    Activations Density 0.173%

    No Known Activations