© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94511
    Prev
    Next
    INDEX
    Explanations

    references to specific performance venues and events

    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
    åĦ
    -0.07
    маз
    -0.07
    Ñĩин
    -0.07
    ocode
    -0.07
    aç
    -0.07
     çıkart
    -0.07
     |--------------------------------------------------------------------------↵
    -0.06
    PRETTY
    -0.06
    owie
    -0.06
    çªģ
    -0.06
    POSITIVE LOGITS
    umba
    0.06
     Eaton
    0.06
    tej
    0.06
    otel
    0.05
    lear
    0.05
    彦
    0.05
     bo
    0.05
     Kingdom
    0.05
    adden
    0.05
    inous
    0.05
    Activations Density 0.019%

    No Known Activations