© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119910
    Prev
    Next
    INDEX
    Explanations

    numeric values related to sports statistics

    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
    qa
    -0.06
     clin
    -0.06
     Slate
    -0.06
    é½
    -0.06
     Manual
    -0.06
    stad
    -0.06
    kas
    -0.06
    ials
    -0.06
     omn
    -0.06
     Cel
    -0.05
    POSITIVE LOGITS
     helicopt
    0.07
    _partner
    0.07
    uard
    0.07
    ä¸Ī
    0.07
    uali
    0.07
    Å¡k
    0.07
     scor
    0.07
    presso
    0.07
    _customize
    0.07
    Knight
    0.06
    Activations Density 0.005%

    No Known Activations