© 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. 77284
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and assurances of reliable service

    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
    æĿī
    -0.07
    ilis
    -0.06
    481
    -0.06
    och
    -0.06
    tru
    -0.06
    apus
    -0.06
     mÃ¼ÅŁ
    -0.06
    abbo
    -0.06
    imap
    -0.06
    iani
    -0.06
    POSITIVE LOGITS
    mere
    0.07
    levator
    0.07
     conveyor
    0.07
     merely
    0.06
    å´ĩ
    0.06
    èįIJ
    0.06
     yola
    0.06
     blindly
    0.06
     yoktur
    0.06
     juste
    0.06
    Activations Density 0.018%

    No Known Activations