© 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 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. 61067
    Prev
    Next
    INDEX
    Explanations

    positive recommendations and evaluations of books or artistic works

    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
    çģ
    -0.08
     æ¥
    -0.07
    izik
    -0.07
    essler
    -0.06
     âĢĮ
    -0.06
    erton
    -0.06
    ardo
    -0.06
    retty
    -0.06
     客
    -0.06
    eson
    -0.06
    POSITIVE LOGITS
     recommendation
    0.09
     recommended
    0.09
    æݨèįIJ
    0.08
    recommend
    0.08
    recommended
    0.08
     recommend
    0.08
     recommends
    0.08
    æݨèĸ¦
    0.07
     recommending
    0.07
     reviewer
    0.07
    Activations Density 0.049%

    No Known Activations