© 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. 120616
    Prev
    Next
    INDEX
    Explanations

    terms related to certain types of media or visual elements

    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
    kus
    -0.07
    ä¸Ģ人
    -0.07
    427
    -0.06
    LAT
    -0.06
     Thompson
    -0.06
    人类
    -0.06
    iek
    -0.06
    .addClass
    -0.06
    idd
    -0.06
    ä¸Ģå¹´
    -0.06
    POSITIVE LOGITS
    ãģŁãĤģãģ®
    0.08
    ãģŁãĤģãģ«
    0.07
    eyh
    0.07
    uegos
    0.07
    olls
    0.07
    bgcolor
    0.06
    rych
    0.06
    zik
    0.06
    ouden
    0.06
     onCancelled
    0.06
    Activations Density 0.006%

    No Known Activations