© 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. 42237
    Prev
    Next
    INDEX
    Explanations

    calls to action urging exploration, participation, and support

    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
    ald
    -0.07
     must
    -0.06
    ↵
    -0.06
     pre
    -0.06
     |
    -0.06
    int
    -0.06
    .googleapis
    -0.06
    ampion
    -0.06
     Dev
    -0.06
     raised
    -0.06
    POSITIVE LOGITS
     yourselves
    0.09
     nhé
    0.09
    /testify
    0.09
    Äįer
    0.08
     prostituer
    0.08
     yourself
    0.08
     rumpe
    0.08
     nakne
    0.08
    vailable
    0.08
    659
    0.07
    Activations Density 0.041%

    No Known Activations