© 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. 17-LLAMASCOPE-RES-131K
    6. 70565
    Prev
    Next
    INDEX
    Explanations

    references to small and medium-sized businesses

    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
    iaux
    -0.08
    dater
    -0.08
    OrCreate
    -0.07
    ave
    -0.07
    lee
    -0.07
     putas
    -0.07
    erken
    -0.07
    lush
    -0.06
    urg
    -0.06
    rott
    -0.06
    POSITIVE LOGITS
    -small
    0.09
     small
    0.08
     medium
    0.07
    small
    0.07
    rin
    0.07
    -scale
    0.07
    /small
    0.07
    -medium
    0.07
     Medium
    0.07
     Small
    0.07
    Activations Density 0.007%

    No Known Activations