© 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. 60070
    Prev
    Next
    INDEX
    Explanations

    references to the location Windsor and related names

    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
    ters
    -0.08
    ting
    -0.08
    ek
    -0.08
    eck
    -0.08
    et
    -0.08
    ey
    -0.07
    InstanceOf
    -0.07
    och
    -0.07
    inson
    -0.07
    okie
    -0.07
    POSITIVE LOGITS
    IENTATION
    0.09
    ment
    0.09
    shire
    0.07
    vale
    0.07
    lili
    0.07
    ORITY
    0.07
    IOUS
    0.07
    antly
    0.07
    ments
    0.06
     Herc
    0.06
    Activations Density 0.004%

    No Known Activations