© 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. 15778
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance and comparison in sports

    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
    iens
    -0.07
    egend
    -0.07
     physic
    -0.06
    _inline
    -0.06
    reeze
    -0.06
    quared
    -0.06
    oux
    -0.06
    keit
    -0.06
     indirectly
    -0.06
    orris
    -0.06
    POSITIVE LOGITS
     underneath
    0.07
    аÑĢан
    0.06
     Mey
    0.06
     circumstance
    0.06
    ichten
    0.06
     dysfunction
    0.06
    PERT
    0.06
     beneath
    0.05
    ë¹Į
    0.05
     Bever
    0.05
    Activations Density 0.022%

    No Known Activations