© 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. 40361
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and timing 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
    برÛĮ
    -0.08
    Loop
    -0.06
    è¨Ģãģ£ãģŁ
    -0.06
    ugins
    -0.06
    /pop
    -0.06
     subsequ
    -0.06
    thouse
    -0.06
    marshall
    -0.06
    ç½²
    -0.06
    کرÛĮ
    -0.06
    POSITIVE LOGITS
     Soros
    0.06
     western
    0.06
    ãĤ«ãĥĨãĤ´ãĥª
    0.06
    -West
    0.05
     legacy
    0.05
    Portland
    0.05
     Pul
    0.05
     native
    0.05
    ga
    0.05
    clair
    0.05
    Activations Density 0.001%

    No Known Activations