© 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. 56194
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related entries

    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
    iew
    -0.06
    ndo
    -0.06
     urban
    -0.06
     LSB
    -0.05
     temp
    -0.05
     Nav
    -0.05
    ushima
    -0.05
    _template
    -0.05
    ies
    -0.05
    levision
    -0.05
    POSITIVE LOGITS
     europé
    0.09
     Europe
    0.09
    continent
    0.09
     europe
    0.09
    nyder
    0.09
     overseas
    0.09
    Europe
    0.09
    æµ·å¤ĸ
    0.09
     european
    0.08
    uropean
    0.08
    Activations Density 0.015%

    No Known Activations