© 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. 127269
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about vehicles

    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
    fos
    -0.07
    VML
    -0.06
    hawk
    -0.06
    ecast
    -0.06
     íĹ
    -0.06
    cores
    -0.06
    odge
    -0.06
    agra
    -0.06
    aml
    -0.06
    erli
    -0.06
    POSITIVE LOGITS
     hydrogen
    0.10
     Hydro
    0.08
     hydr
    0.08
    bsite
    0.07
    Å¡ak
    0.07
    á»ĭch
    0.07
    hydr
    0.07
     tod
    0.07
    διο
    0.07
    hydro
    0.07
    Activations Density 0.015%

    No Known Activations