© 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. 73531
    Prev
    Next
    INDEX
    Explanations

    terms associated with complex situations and actions, particularly in contexts involving risk or medical issues

    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
    kle
    -0.09
    ůj
    -0.08
    inium
    -0.08
    anders
    -0.08
    FieldValue
    -0.08
    edback
    -0.08
    .scalablytyped
    -0.08
    (æĹ¥
    -0.08
    Ø´ÛĮ
    -0.08
    preload
    -0.08
    POSITIVE LOGITS
     or
    0.09
     then
    0.09
     means
    0.08
     often
    0.08
    then
    0.07
    ?
    0.07
     if
    0.07
    ?↵
    0.07
     sometimes
    0.07
     when
    0.07
    Activations Density 0.109%

    No Known Activations