© 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. 130916
    Prev
    Next
    INDEX
    Explanations

    terms related to sports statistics and performance assessments

    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
    ascar
    -0.07
     ister
    -0.07
    ipop
    -0.06
    ayload
    -0.06
    pagesize
    -0.06
    nier
    -0.06
    ackages
    -0.06
     Language
    -0.06
    çĶ²
    -0.06
    oggle
    -0.06
    POSITIVE LOGITS
     execution
    0.07
     leadership
    0.07
    afi
    0.06
     youthful
    0.06
     im
    0.06
    atti
    0.06
    аÑĤÑĸ
    0.06
    oord
    0.06
     timely
    0.05
     Scheme
    0.05
    Activations Density 0.043%

    No Known Activations