© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 86782
    Prev
    Next
    INDEX
    Explanations

    references to the "Formula" concept, specifically in a racing or performance context

    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
    rot
    -0.08
    elper
    -0.07
    ening
    -0.07
    rog
    -0.07
    house
    -0.07
    àµįà´
    -0.06
    esis
    -0.06
    fall
    -0.06
    rogen
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
    e
    0.09
    ative
    0.07
    oeff
    0.07
    ulario
    0.07
    ayout
    0.07
    icari
    0.07
    tte
    0.07
    ular
    0.07
     dÄ±ÅŁÄ±
    0.07
     errorCallback
    0.07
    Activations Density 0.012%

    No Known Activations