© 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. 9-LLAMASCOPE-RES-131K
    11. 95039
    Prev
    Next
    INDEX
    Explanations

    references to art exhibitions and group shows

    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
    meer
    -0.08
    strand
    -0.08
    esco
    -0.07
    ÐĽÐ¬
    -0.07
    )[:
    -0.07
    ditor
    -0.07
    عÙĨ
    -0.07
    /Dk
    -0.07
    oxel
    -0.07
    itable
    -0.07
    POSITIVE LOGITS
    lash
    0.07
    OUCH
    0.07
    swer
    0.06
    ither
    0.06
    omap
    0.06
     Dunn
    0.06
    CTest
    0.06
    acre
    0.06
    ecom
    0.06
     sew
    0.06
    Activations Density 0.008%

    No Known Activations