© 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 EvalsExportsinterp-engineNEWAPI 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. 2619
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceutical professionals and related practices

    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
    loth
    -0.06
    othy
    -0.06
    sez
    -0.06
    /he
    -0.06
    ILLISECONDS
    -0.06
    rega
    -0.05
    apan
    -0.05
    pcm
    -0.05
    znam
    -0.05
     diluted
    -0.05
    POSITIVE LOGITS
    -Compatible
    0.08
    edor
    0.07
    aldi
    0.07
    âĢ¦)↵↵
    0.07
    ëĦ·
    0.07
    eç
    0.07
     Campo
    0.07
     converge
    0.06
    aphrag
    0.06
    iê
    0.06
    Activations Density 0.003%

    No Known Activations