© 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. 126504
    Prev
    Next
    INDEX
    Explanations

    words related to historical origins or original intentions

    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
    	Copyright
    -0.07
     newObj
    -0.06
     new
    -0.06
    :checked
    -0.06
    uli
    -0.06
    loud
    -0.06
     heritage
    -0.06
     finally
    -0.06
    elize
    -0.06
     recent
    -0.06
    POSITIVE LOGITS
     originally
    0.08
    [section
    0.08
     intended
    0.08
     initially
    0.08
     yalnızca
    0.07
     called
    0.07
    arker
    0.07
    called
    0.07
    /original
    0.07
     only
    0.07
    Activations Density 0.025%

    No Known Activations