© 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 EvalsExportsAPI 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. 59397
    Prev
    Next
    INDEX
    Explanations

    references to the act of diving in various contexts

    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
    lier
    -0.10
    liche
    -0.09
    entar
    -0.08
    ted
    -0.08
     rost
    -0.08
    lijk
    -0.07
    ness
    -0.07
    rophe
    -0.07
    aurus
    -0.07
    mente
    -0.07
    POSITIVE LOGITS
     deeper
    0.09
    /div
    0.09
     deep
    0.08
     depths
    0.07
     sâu
    0.07
    deep
    0.07
    ault
    0.07
     deepest
    0.07
    ŀ
    0.06
    Deep
    0.06
    Activations Density 0.007%

    No Known Activations