© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 84248
    Prev
    Next
    INDEX
    Explanations

    references to licensing terms and copyright 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
     straw
    -0.07
     pride
    -0.07
     sai
    -0.06
     UIB
    -0.06
    outs
    -0.06
    ÐļТ
    -0.06
     Ree
    -0.06
    278
    -0.06
    ipo
    -0.06
     Rowe
    -0.06
    POSITIVE LOGITS
    /by
    0.07
    .bundle
    0.06
    lav
    0.06
    éº
    0.05
    laws
    0.05
    uth
    0.05
     rub
    0.05
    \\/
    0.05
     licenses
    0.05
    ERM
    0.05
    Activations Density 0.001%

    No Known Activations