© 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. 128842
    Prev
    Next
    INDEX
    Explanations

    French words and phrases related to agreements or partnerships

    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
    åİ
    -0.07
     hang
    -0.06
    017
    -0.06
     Carpenter
    -0.06
     Hang
    -0.06
     Cruc
    -0.06
     ‘
    -0.06
    Hang
    -0.06
     Mats
    -0.06
    hang
    -0.05
    POSITIVE LOGITS
    Äħż
    0.08
    aÄį
    0.07
    enor
    0.07
    atee
    0.06
    è»
    0.06
    udos
    0.06
    erken
    0.06
     accessor
    0.06
    añ
    0.06
    .gridView
    0.06
    Activations Density 0.000%

    No Known Activations