© 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. 39986
    Prev
    Next
    INDEX
    Explanations

    descriptions of aquatic environments and associated activities

    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
    ëĬIJ
    -0.07
    fal
    -0.07
    odable
    -0.07
    ziej
    -0.07
    essenger
    -0.07
    hear
    -0.06
    asso
    -0.06
     memnun
    -0.06
    thag
    -0.06
    conds
    -0.06
    POSITIVE LOGITS
     deck
    0.08
     Deck
    0.07
     Owner
    0.07
    enet
    0.07
     hatch
    0.06
    deck
    0.06
     configuration
    0.06
     Commod
    0.06
     compromised
    0.06
    aron
    0.06
    Activations Density 0.004%

    No Known Activations