© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83684
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences with illness and recovery

    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
     migrationBuilder
    -0.08
    latable
    -0.07
    ¶Į
    -0.07
    ãģĭãĤı
    -0.07
    лÑĸÑĤ
    -0.07
    heed
    -0.07
    PFN
    -0.07
    .onView
    -0.07
    æĺĩ
    -0.06
     petit
    -0.06
    POSITIVE LOGITS
     isolation
    0.07
     Polymer
    0.07
     tests
    0.07
    owler
    0.07
     TEST
    0.07
     testing
    0.06
     symptom
    0.06
     isolate
    0.06
     Testing
    0.06
     PCR
    0.06
    Activations Density 0.004%

    No Known Activations