© 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. 4887
    Prev
    Next
    INDEX
    Explanations

    mentions of kayaking lessons and sessions

    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
    nict
    -0.07
    GGLE
    -0.06
    ÑĢади
    -0.06
    bern
    -0.06
    aud
    -0.06
    NECT
    -0.06
    VERSE
    -0.06
     ********************************************************************************
    -0.06
    acceptable
    -0.06
    voj
    -0.06
    POSITIVE LOGITS
     learning
    0.07
    -learning
    0.07
     weather
    0.07
     safety
    0.07
     intermedi
    0.07
     Safety
    0.07
    erval
    0.07
    Safety
    0.07
    Learning
    0.07
    lernen
    0.07
    Activations Density 0.008%

    No Known Activations