© 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. 85730
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts that signify surpassing traditional limits or expectations

    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
    igan
    -0.08
     Futures
    -0.07
     chung
    -0.07
    inize
    -0.07
    AMP
    -0.07
     hrom
    -0.07
    ì°¬
    -0.07
     sperma
    -0.07
    æ³Ĭ
    -0.07
    ober
    -0.07
    POSITIVE LOGITS
     mere
    0.12
     beyond
    0.09
     Beyond
    0.09
    Beyond
    0.09
     the
    0.09
    -the
    0.08
     merely
    0.08
     reach
    0.07
    most
    0.07
    mere
    0.07
    Activations Density 0.012%

    No Known Activations