© 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. 82851
    Prev
    Next
    INDEX
    Explanations

    significant actions or events that have impacted society or history

    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
    ennes
    -0.08
    dÃŃ
    -0.07
    aze
    -0.07
     plenty
    -0.07
    ocker
    -0.07
     Plenty
    -0.06
    orio
    -0.06
     VERY
    -0.06
    gado
    -0.06
    nul
    -0.06
    POSITIVE LOGITS
     nor
    0.10
     sheer
    0.09
    å¦ĤæѤ
    0.08
     tolik
    0.08
     à¤ĩतन
    0.07
     tão
    0.07
     ÏĦÏĮÏĥο
    0.07
     anymore
    0.06
     combination
    0.06
    ì²ĺëŁ¼
    0.06
    Activations Density 0.025%

    No Known Activations