© 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. 14839
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons and comparative language

    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
    anik
    -0.08
    idel
    -0.07
    оÑĥ
    -0.07
     Marr
    -0.07
    vor
    -0.07
    urons
    -0.07
     Vall
    -0.07
     Bott
    -0.07
    Æ°á»Ŀng
    -0.07
    trag
    -0.06
    POSITIVE LOGITS
     between
    0.13
    between
    0.10
     comparison
    0.10
     мÑĸж
    0.09
     tussen
    0.09
     Between
    0.09
    Between
    0.09
     междÑĥ
    0.09
    comparison
    0.08
     giữa
    0.08
    Activations Density 0.012%

    No Known Activations