© 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. 17268
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "By" indicating authorship or attribution

    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
    ами
    -0.07
    ients
    -0.07
    ught
    -0.07
    ping
    -0.07
    duct
    -0.06
     Cove
    -0.06
    curring
    -0.06
    stm
    -0.06
    lio
    -0.06
     OA
    -0.06
    POSITIVE LOGITS
     contrast
    0.08
    contrast
    0.08
     chance
    0.08
    ron
    0.08
     far
    0.07
    fleet
    0.07
    íĥĪ
    0.07
    734
    0.07
    kle
    0.07
    až
    0.07
    Activations Density 0.013%

    No Known Activations