© 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. 17387
    Prev
    Next
    INDEX
    Explanations

    scholarly references and academic citations

    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
    ORY
    -0.08
     Vin
    -0.07
     Columbia
    -0.07
     Ahmet
    -0.06
     Shank
    -0.06
     Kerala
    -0.06
    avn
    -0.06
     Sinh
    -0.06
    pri
    -0.06
     PIO
    -0.06
    POSITIVE LOGITS
     Texas
    0.09
     Dallas
    0.08
     Texans
    0.08
     Rangers
    0.08
    Dallas
    0.08
    Texas
    0.07
     texas
    0.07
     Dust
    0.07
     Nigeria
    0.07
     Sadd
    0.07
    Activations Density 0.009%

    No Known Activations