© 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. 130665
    Prev
    Next
    INDEX
    Explanations

    technical specifications and comparisons related to devices or products

    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
    eyim
    -0.07
    InputBorder
    -0.07
    UIL
    -0.07
    iset
    -0.06
    -quote
    -0.06
    /umd
    -0.06
    amac
    -0.06
    oÄŁ
    -0.06
    तम
    -0.06
     ëĦ¤ìĿ´íĬ¸
    -0.06
    POSITIVE LOGITS
     traditional
    0.33
     conventional
    0.32
     usual
    0.28
     normal
    0.27
    traditional
    0.26
     Traditional
    0.24
    Traditional
    0.23
    usual
    0.23
     regular
    0.22
     ordinary
    0.22
    Activations Density 0.190%

    No Known Activations