© 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. 17797
    Prev
    Next
    INDEX
    Explanations

    numerical values and financial references

    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
    utas
    -0.07
    lý
    -0.06
    00
    -0.06
    oshi
    -0.06
    488
    -0.06
     Loose
    -0.06
    ÑģÑĤÑĥп
    -0.06
    uras
    -0.06
    ãĢģ“
    -0.06
    932
    -0.06
    POSITIVE LOGITS
     bis
    0.06
    elerin
    0.06
    imen
    0.06
     Bis
    0.06
     Propel
    0.06
     plus
    0.06
     again
    0.06
     str
    0.06
     +↵
    0.05
     Silver
    0.05
    Activations Density 0.033%

    No Known Activations