© 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. 128337
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming keywords or function 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
    org
    -0.07
    -alist
    -0.07
    lette
    -0.06
    ingle
    -0.06
    avig
    -0.06
    azzi
    -0.06
     Crime
    -0.06
    Ļ
    -0.06
    yte
    -0.06
    uze
    -0.06
    POSITIVE LOGITS
    ustos
    0.07
    olley
    0.07
    0.06
    abet
    0.06
    ylland
    0.06
    Binder
    0.06
    ì§Ħ
    0.06
    nts
    0.06
    ether
    0.06
    etus
    0.06
    Activations Density 0.000%

    No Known Activations