© 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. 93873
    Prev
    Next
    INDEX
    Explanations

    references to health tracking and logging activities related to diet and wellness

    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
    lod
    -0.07
    oola
    -0.07
     kraj
    -0.06
     daleko
    -0.06
     гÑĥб
    -0.06
    /maps
    -0.06
    edn
    -0.06
    LATED
    -0.06
     print
    -0.06
     Sage
    -0.06
    POSITIVE LOGITS
     weight
    0.07
     weigh
    0.07
     importer
    0.07
     journal
    0.07
     record
    0.07
     célib
    0.06
    OCI
    0.06
    entries
    0.06
     daily
    0.06
    PRO
    0.06
    Activations Density 0.020%

    No Known Activations