© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56265
    Prev
    Next
    INDEX
    Explanations

    mentions of recycled or creatively reused items and furniture

    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
    shirt
    -0.07
     Locker
    -0.06
     erection
    -0.06
    locker
    -0.06
    .bundle
    -0.06
    sed
    -0.06
    Locker
    -0.06
    izon
    -0.06
    uml
    -0.06
    /gl
    -0.06
    POSITIVE LOGITS
     Craigslist
    0.08
     pains
    0.06
    andel
    0.06
    igslist
    0.06
    oyer
    0.06
    enschaft
    0.06
     Restoration
    0.06
     eBay
    0.06
     Acquisition
    0.06
     Handles
    0.06
    Activations Density 0.007%

    No Known Activations