© 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. 82907
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and health conditions in sports 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
     DropIndex
    -0.07
    ripple
    -0.07
    Permanent
    -0.06
    ÙĪÛĮÙĩ
    -0.06
    isku
    -0.06
    duk
    -0.06
    =yes
    -0.06
     informal
    -0.06
    ówn
    -0.06
    spiel
    -0.06
    POSITIVE LOGITS
     minor
    0.07
     Minor
    0.06
    elli
    0.06
    ère
    0.06
    thes
    0.06
     Lambert
    0.06
     unspecified
    0.06
    tons
    0.06
     Zot
    0.06
     back
    0.05
    Activations Density 0.011%

    No Known Activations