© 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. 15-LLAMASCOPE-RES-131K
    11. 26504
    Prev
    Next
    INDEX
    Explanations

    mentions of sports performances and outcomes

    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
    ÑĢаб
    -0.08
    .POS
    -0.07
    .WebControls
    -0.07
    acades
    -0.07
    avaÅŁ
    -0.07
    ocab
    -0.07
    casecmp
    -0.07
    ValuePair
    -0.07
    دد
    -0.07
    .updateDynamic
    -0.07
    POSITIVE LOGITS
    loss
    0.09
     loss
    0.09
    Loss
    0.08
     Loss
    0.08
     losses
    0.07
     LOSS
    0.07
    lose
    0.07
    LOSS
    0.07
    eg
    0.06
     lose
    0.06
    Activations Density 0.025%

    No Known Activations