© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83681
    Prev
    Next
    INDEX
    Explanations

    references to service offerings and client assistance

    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
    Ø¢Ùħ
    -0.07
    ago
    -0.07
    žel
    -0.06
    rox
    -0.06
    enville
    -0.06
    gne
    -0.06
     suction
    -0.06
    ãĥªãĥ³
    -0.06
     èĢĮ
    -0.06
    azon
    -0.06
    POSITIVE LOGITS
     for
    0.08
     afford
    0.07
    ons
    0.07
    kp
    0.07
    for
    0.07
     длÑı
    0.07
    316
    0.07
     für
    0.06
    	for
    0.06
    327
    0.06
    Activations Density 0.027%

    No Known Activations