© 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. 17-LLAMASCOPE-RES-131K
    11. 73498
    Prev
    Next
    INDEX
    Explanations

    references to specific playwrights and their works

    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
     folks
    -0.07
     Kraj
    -0.06
     Freedom
    -0.06
     Millet
    -0.06
    708
    -0.06
     Posts
    -0.06
    hra
    -0.06
     cow
    -0.06
    Freedom
    -0.06
    ê·¹
    -0.06
    POSITIVE LOGITS
     himself
    0.10
    ian
    0.10
    ovky
    0.08
    ians
    0.08
    iana
    0.08
    's
    0.08
    ův
    0.08
    ean
    0.08
    oland
    0.08
    ìľ¼ëĭĪ
    0.07
    Activations Density 0.021%

    No Known Activations