© 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. 27973
    Prev
    Next
    INDEX
    Explanations

    instructions related to mixing and preparing food

    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
    ÑĤеÑĢи
    -0.07
    elter
    -0.07
    ahy
    -0.07
    è
    -0.06
    olist
    -0.06
    ataka
    -0.06
    á»ī
    -0.06
    ̧
    -0.06
    etsk
    -0.06
    رÙĪÛĮ
    -0.06
    POSITIVE LOGITS
     settling
    0.10
     settle
    0.10
     Sed
    0.09
     sediment
    0.09
     settled
    0.09
     suspended
    0.08
     settlement
    0.08
     settles
    0.08
     Settlement
    0.07
     sed
    0.07
    Activations Density 0.016%

    No Known Activations