© 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. 82991
    Prev
    Next
    INDEX
    Explanations

    specific frequencies or measures related to scientific data and statistical results

    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
    ｡
    -0.10
    ,eg
    -0.10
    erdem
    -0.09
    åIJįçĦ¡ãģĹ
    -0.09
    íĤ
    -0.09
    .Îł
    -0.09
    иÑģлов
    -0.09
     mastur
    -0.09
    .Îķ
    -0.09
     birik
    -0.09
    POSITIVE LOGITS
     dit
    0.09
     and
    0.08
    Âł
    0.07
    *
    0.07
     etc
    0.07
    ),
    0.07
    0.07
     *
    0.07
     &
    0.07
    i
    0.07
    Activations Density 0.095%

    No Known Activations