© 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. 88095
    Prev
    Next
    INDEX
    Explanations

    references to specific islands and territories

    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
    neau
    -0.08
    abase
    -0.07
    aliz
    -0.07
    771
    -0.07
    egas
    -0.07
    isman
    -0.07
    nte
    -0.07
    edia
    -0.07
    latable
    -0.07
    бина
    -0.06
    POSITIVE LOGITS
    erman
    0.07
     Howe
    0.06
    ering
    0.06
     chức
    0.06
    éĻ°
    0.06
     íļ
    0.06
    endor
    0.06
    vé
    0.06
    Ùıر
    0.06
    ynes
    0.06
    Activations Density 0.003%

    No Known Activations