© 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. 127513
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" in various forms and contexts

    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
    undra
    -0.07
    ammad
    -0.07
    ailer
    -0.07
    ÏĢÏĮ
    -0.07
    iless
    -0.07
    æŁı
    -0.07
    inkle
    -0.07
    enus
    -0.07
    ettle
    -0.06
    uels
    -0.06
    POSITIVE LOGITS
     that
    0.08
     an
    0.07
     a
    0.07
    avia
    0.06
    phin
    0.06
    :
    0.06
     something
    0.06
    834
    0.06
     increased
    0.06
     bahwa
    0.06
    Activations Density 0.006%

    No Known Activations