© 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. 15-LLAMASCOPE-RES-131K
    11. 89103
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to measurements and variables

    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
    anson
    -0.06
    ialog
    -0.06
     global
    -0.06
    Å¡k
    -0.06
     offices
    -0.06
    plets
    -0.06
    alette
    -0.06
     share
    -0.06
    ocache
    -0.06
    myp
    -0.06
    POSITIVE LOGITS
    freq
    0.07
    -frequency
    0.07
     pitch
    0.07
    pitch
    0.07
    frequency
    0.07
    eya
    0.07
    Pitch
    0.07
     Frequ
    0.07
     frequency
    0.07
     freq
    0.07
    Activations Density 0.094%

    No Known Activations