© 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. 58123
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities along with their associated context

    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
    agan
    -0.07
    æİĽ
    -0.06
    ovu
    -0.06
     Cay
    -0.05
     Gems
    -0.05
    brands
    -0.05
    uel
    -0.05
    ools
    -0.05
     Giuliani
    -0.05
    onto
    -0.05
    POSITIVE LOGITS
    efon
    0.07
    UCKET
    0.07
    582
    0.07
    uppen
    0.06
     cand
    0.06
    ARGET
    0.06
    879
    0.06
    877
    0.06
    _semaphore
    0.06
     steps
    0.06
    Activations Density 0.014%

    No Known Activations