© 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. 54169
    Prev
    Next
    INDEX
    Explanations

    references to television ratings and scheduling details

    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
    à¹ģà¸ģ
    -0.06
    auge
    -0.06
     Chips
    -0.06
    _region
    -0.06
     organic
    -0.05
    佩
    -0.05
    ½æķ°
    -0.05
     minib
    -0.05
    znik
    -0.05
    nor
    -0.05
    POSITIVE LOGITS
     Kültür
    0.09
     Cumhur
    0.07
    æķ
    0.07
    _AA
    0.07
    ائÙĤ
    0.07
     âĢª
    0.07
    ohen
    0.07
    ezier
    0.07
     puta
    0.07
     Deutsch
    0.07
    Activations Density 0.021%

    No Known Activations