© 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. 59985
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and court proceedings

    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
    uste
    -0.08
    heck
    -0.08
     å¹
    -0.08
    GMEM
    -0.08
    Äł
    -0.08
    rift
    -0.07
    åĴ¨
    -0.07
    _CURSOR
    -0.07
    OffsetTable
    -0.07
    _mD
    -0.07
    POSITIVE LOGITS
     staying
    0.07
    izio
    0.07
     pending
    0.06
     stay
    0.06
    mts
    0.06
     conditions
    0.06
     Flake
    0.06
     orders
    0.06
     watchers
    0.06
     sticker
    0.05
    Activations Density 0.006%

    No Known Activations