© 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. 93275
    Prev
    Next
    INDEX
    Explanations

    statistical data related to lowest and highest records or rates

    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
    ropp
    -0.08
    ABCDEFGHIJKLMNOP
    -0.08
    飾
    -0.08
     Yön
    -0.08
    assi
    -0.08
    ICODE
    -0.07
     MÃľ
    -0.07
    åĢĻ
    -0.07
     salopes
    -0.07
    AMA
    -0.07
    POSITIVE LOGITS
    0.08
     indicator
    0.08
    Indicator
    0.07
     indicators
    0.07
     per
    0.07
     Indicator
    0.07
     Index
    0.07
     index
    0.06
     liter
    0.06
    indicator
    0.06
    Activations Density 0.028%

    No Known Activations