© 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. 29233
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and influences in creative work

    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
    õ
    -0.06
     anyone
    -0.06
    aru
    -0.06
     详æĥħ
    -0.06
    ux
    -0.06
    rim
    -0.06
    uppe
    -0.06
    ë¿IJ
    -0.06
     only
    -0.05
     totiž
    -0.05
    POSITIVE LOGITS
    )?↵
    0.10
     yourselves
    0.09
    ä½łçļĦ
    0.09
    ï¼Ł↵
    0.09
     yourself
    0.09
    ãģ§ãģĻãģĭ
    0.09
     istediÄŁiniz
    0.08
    ëĤĺìļĶ
    0.08
    ?↵
    0.07
    )?↵↵
    0.07
    Activations Density 0.115%

    No Known Activations