© 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. 4163
    Prev
    Next
    INDEX
    Explanations

    occurrences of formal events and significant historical timelines

    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
    åde
    -0.07
    ãģĭãģĹ
    -0.07
    ÑĢÑĥб
    -0.07
     latest
    -0.07
    СÐŀ
    -0.07
     orchest
    -0.06
    icari
    -0.06
    ãĤ¸ãĤª
    -0.06
    ì²Ļ
    -0.06
    ëŀĮ
    -0.06
    POSITIVE LOGITS
     ever
    0.07
     rud
    0.07
    -ever
    0.06
     mere
    0.06
     followed
    0.06
     EVER
    0.06
     shortly
    0.06
     ceremon
    0.06
     famously
    0.06
    esel
    0.06
    Activations Density 0.050%

    No Known Activations