© 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. 9-LLAMASCOPE-RES-131K
    11. 97614
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "to."

    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
    edi
    -0.08
    thest
    -0.07
    edom
    -0.07
    pio
    -0.07
    ties
    -0.06
    ever
    -0.06
    usercontent
    -0.06
    CAD
    -0.06
    wyn
    -0.06
    bil
    -0.06
    POSITIVE LOGITS
    988
    0.07
    اØŃØ©
    0.07
     Bened
    0.07
    orex
    0.06
     punt
    0.06
    ucher
    0.06
    Forgery
    0.06
    iant
    0.06
    uluk
    0.06
    ovky
    0.06
    Activations Density 0.015%

    No Known Activations