© 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. 127394
    Prev
    Next
    INDEX
    Explanations

    timestamps and specific time-related information

    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
     Near
    -0.06
     Gust
    -0.06
     alias
    -0.06
    lung
    -0.06
    æĢĿ
    -0.05
     Far
    -0.05
    ifen
    -0.05
    ichen
    -0.05
    oi
    -0.05
    ked
    -0.05
    POSITIVE LOGITS
    ÑĢоÑģÑĤо
    0.08
    _DECLS
    0.08
    _IMPLEMENT
    0.07
    rawer
    0.07
    TEL
    0.07
    _WARNINGS
    0.07
     меÑħ
    0.07
    	UObject
    0.07
    %p
    0.07
     диви
    0.07
    Activations Density 0.003%

    No Known Activations