© 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. 15-LLAMASCOPE-RES-131K
    11. 89454
    Prev
    Next
    INDEX
    Explanations

    references to original or unaltered versions of artistic work

    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
    ony
    -0.06
    onym
    -0.06
    rede
    -0.06
    404
    -0.06
     Leisure
    -0.05
    rate
    -0.05
     Liv
    -0.05
     Substitute
    -0.05
     voks
    -0.05
    ux
    -0.05
    POSITIVE LOGITS
     natural
    0.12
     raw
    0.11
    natural
    0.10
    /raw
    0.09
     Raw
    0.09
    åİŁå§ĭ
    0.09
     Natural
    0.09
    (raw
    0.09
    RAW
    0.09
    Natural
    0.09
    Activations Density 0.019%

    No Known Activations