© 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. 30457
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases that emphasize comparative qualities

    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
     remainder
    -0.07
     Than
    -0.06
    afil
    -0.06
    uze
    -0.06
     than
    -0.06
     rest
    -0.06
    elve
    -0.06
    insky
    -0.06
    oningen
    -0.06
    sbin
    -0.06
    POSITIVE LOGITS
    ãĤĤãģ£ãģ¨
    0.09
     least
    0.08
    rou
    0.08
    least
    0.07
    ittest
    0.07
     rou
    0.07
     most
    0.07
     cra
    0.07
     absolutely
    0.07
    itest
    0.07
    Activations Density 0.019%

    No Known Activations