© 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. 69203
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases that indicate improvement or positive action

    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
     totiž
    -0.11
     ìŀĪê³ł
    -0.09
    ãģ¾ãģļ
    -0.09
    	and
    -0.08
     и
    -0.08
     vÃł
    -0.08
     alıp
    -0.07
     anda
    -0.07
    ãĢģæľ¬
    -0.07
     firstly
    -0.07
    POSITIVE LOGITS
     other
    0.09
     others
    0.09
     alike
    0.08
    /or
    0.08
     consequently
    0.07
     дÑĢÑĥгие
    0.07
    ollider
    0.07
    etc
    0.07
     etc
    0.07
    alem
    0.07
    Activations Density 0.147%

    No Known Activations