© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85014
    Prev
    Next
    INDEX
    Explanations

    expressions related to comparisons and contrasts

    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
    ä¸į
    -0.07
    rou
    -0.06
    Disclosure
    -0.06
    rane
    -0.06
    ä¸įåĪ°
    -0.06
     not
    -0.06
    onis
    -0.06
    ardless
    -0.06
     no
    -0.06
    rous
    -0.06
    POSITIVE LOGITS
     rather
    0.09
    rather
    0.09
     Rather
    0.08
    Rather
    0.08
     spÃŃÅ¡e
    0.08
    ÑĪиб
    0.07
    âĸį
    0.07
    ÏĢÏīÏĤ
    0.07
     ìĺ
    0.07
     sondern
    0.07
    Activations Density 0.010%

    No Known Activations