© 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. 120235
    Prev
    Next
    INDEX
    Explanations

    references to food-related contexts and large-scale systems

    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
    enheim
    -0.07
    ras
    -0.06
    dit
    -0.06
     conditions
    -0.06
     jeg
    -0.06
    нÑĮ
    -0.06
    221
    -0.06
    ãĥ³ãĤ¹
    -0.06
    421
    -0.06
    ãĤ¹ãĥĨãĤ£
    -0.06
    POSITIVE LOGITS
    /big
    0.09
    -big
    0.09
    -scale
    0.09
    ãĢģ大
    0.08
     chunk
    0.08
    (big
    0.07
    ots
    0.07
     strides
    0.07
     spender
    0.07
     scale
    0.07
    Activations Density 0.119%

    No Known Activations