© 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. 127181
    Prev
    Next
    INDEX
    Explanations

    references to events occurring after a specific timeline or announcement

    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
    _DECLS
    -0.07
     norge
    -0.07
    linik
    -0.07
    iner
    -0.07
    ets
    -0.07
    eter
    -0.07
    .SizeType
    -0.07
    OMUX
    -0.07
    CallCheck
    -0.07
    eras
    -0.07
    POSITIVE LOGITS
     another
    0.07
     celebrated
    0.07
     we
    0.07
     ones
    0.07
     ÙħÛĮÙĦادÛĮ
    0.06
    olet
    0.05
    irthday
    0.05
    ived
    0.05
     publication
    0.05
     directly
    0.05
    Activations Density 0.012%

    No Known Activations