© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 430
    Prev
    Next
    INDEX
    Explanations

    references to expenses and financial summaries

    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
    âl
    -0.07
    emble
    -0.07
    rove
    -0.07
    ernel
    -0.06
    ith
    -0.06
    aeper
    -0.06
    indr
    -0.06
     Schl
    -0.06
    ufe
    -0.06
     kab
    -0.06
    POSITIVE LOGITS
     nor
    0.17
     Nor
    0.17
    Nor
    0.14
    nor
    0.12
     NOR
    0.10
     separate
    0.08
     neither
    0.08
     only
    0.07
     seperate
    0.07
     merely
    0.07
    Activations Density 0.034%

    No Known Activations