© 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. 4562
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" in various contexts

    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
    åıĤçħ§
    -0.06
    hal
    -0.06
    inja
    -0.06
    lea
    -0.06
    enburg
    -0.06
    thon
    -0.06
     إذ
    -0.06
    ’ÑĶ
    -0.06
    ston
    -0.06
    upy
    -0.06
    POSITIVE LOGITS
    ernel
    0.07
    ripper
    0.07
    endo
    0.07
    anos
    0.07
    igte
    0.07
    ÙĪÛĮÙĩ
    0.07
     ÙģØ¥ÙĨ
    0.07
    RAINT
    0.06
    umm
    0.06
    åĩ¯
    0.06
    Activations Density 0.003%

    No Known Activations