© 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. 104943
    Prev
    Next
    INDEX
    Explanations

    references to individuals' educational backgrounds and career paths

    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
     addCriterion
    -0.09
    ataka
    -0.08
    nip
    -0.08
    Printf
    -0.08
    orWhere
    -0.08
    izon
    -0.07
    #echo
    -0.07
    iyon
    -0.07
    orate
    -0.07
    ifen
    -0.07
    POSITIVE LOGITS
     frequently
    0.07
     twice
    0.06
     sucker
    0.06
     often
    0.06
     former
    0.06
     recently
    0.06
     consequently
    0.06
    abel
    0.06
     frequent
    0.06
    inde
    0.06
    Activations Density 0.031%

    No Known Activations