© 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. 83377
    Prev
    Next
    INDEX
    Explanations

    references to types of coffee tables, particularly those with vintage or antique styles

    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
     Uncategorized
    -0.08
     Fol
    -0.07
    ursed
    -0.07
    rary
    -0.07
    itus
    -0.06
    ills
    -0.06
    issen
    -0.06
    atchet
    -0.06
    BERS
    -0.06
    fol
    -0.06
    POSITIVE LOGITS
    844
    0.07
    htm
    0.07
    994
    0.06
    796
    0.06
    æĻ®
    0.06
    iment
    0.06
     Hindered
    0.06
    xl
    0.06
    ën
    0.06
    .wrap
    0.06
    Activations Density 0.003%

    No Known Activations