© 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. 15-LLAMASCOPE-RES-131K
    11. 87988
    Prev
    Next
    INDEX
    Explanations

    words that convey a sense of frequency or emphasis

    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
    sg
    -0.09
    .scalablytyped
    -0.07
    Unchecked
    -0.07
    ially
    -0.07
     Duis
    -0.07
    icolon
    -0.07
    غاÙĦ
    -0.07
    Cho
    -0.07
    //**↵
    -0.07
    üçük
    -0.07
    POSITIVE LOGITS
    ãĥ¼ãĥī
    0.07
    /not
    0.07
    noon
    0.07
    ($('.
    0.06
    rics
    0.06
    cation
    0.06
    Ñı
    0.06
    ness
    0.06
    te
    0.06
    yn
    0.06
    Activations Density 0.063%

    No Known Activations