© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91738
    Prev
    Next
    INDEX
    Explanations

    terms related to the field of science or academia, specifically referencing studies and theories

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    vre
    -0.06
    essed
    -0.06
     Frog
    -0.06
    active
    -0.06
    è¯Ŀ
    -0.06
    hem
    -0.06
     Sap
    -0.06
     cdecl
    -0.06
    isters
    -0.06
    },{↵
    -0.06
    POSITIVE LOGITS
    gang
    0.08
    eldo
    0.07
    434
    0.07
    -Origin
    0.07
    quets
    0.07
     errorCallback
    0.07
    iland
    0.07
    prung
    0.07
    PEND
    0.06
    hiro
    0.06
    Activations Density 0.028%

    No Known Activations