© 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. 30254
    Prev
    Next
    INDEX
    Explanations

    significant historical landmarks and their descriptions

    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
    uil
    -0.06
    rido
    -0.06
     Santos
    -0.06
    irut
    -0.06
     Freund
    -0.06
    emoc
    -0.06
    etta
    -0.06
    reative
    -0.06
    arget
    -0.06
     benches
    -0.06
    POSITIVE LOGITS
     palace
    0.09
    à¸ŀระราà¸Ĭ
    0.09
    æķ·
    0.08
     royal
    0.08
     residence
    0.07
    èĨ
    0.07
     Buckingham
    0.07
     roy
    0.07
     Residence
    0.07
     Palace
    0.07
    Activations Density 0.011%

    No Known Activations