© 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. 82949
    Prev
    Next
    INDEX
    Explanations

    activities and exercises related to creativity and movement

    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
    dete
    -0.07
     incom
    -0.07
     adm
    -0.06
    .Win
    -0.06
    dej
    -0.06
     KO
    -0.06
     flaw
    -0.06
    /ajax
    -0.06
     sez
    -0.06
    -enh
    -0.06
    POSITIVE LOGITS
    ÏĦεÏģ
    0.07
    AGMA
    0.07
    祥
    0.07
    asia
    0.07
    elden
    0.07
    esk
    0.07
    èo
    0.06
    arium
    0.06
    Ñģи
    0.06
    otime
    0.06
    Activations Density 0.006%

    No Known Activations