© 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. 126641
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or aspirations

    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
    borg
    -0.07
    ube
    -0.07
    enas
    -0.07
    planet
    -0.06
     Delegate
    -0.06
    osg
    -0.06
    .opengl
    -0.06
    undi
    -0.06
    exus
    -0.06
    ogan
    -0.06
    POSITIVE LOGITS
    =sc
    0.06
    reste
    0.06
     fame
    0.06
    .await
    0.06
    koa
    0.06
    عÙħÙĦ
    0.06
    ãĥ¼ãĥ©
    0.06
    pit
    0.06
     opportunity
    0.06
    Sc
    0.06
    Activations Density 0.019%

    No Known Activations