© 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. 60039
    Prev
    Next
    INDEX
    Explanations

    prominent names and references in the text

    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
    æŁĦ
    -0.08
    ventus
    -0.08
    elerik
    -0.08
    ãģĵãĤĵãģ«
    -0.08
    èo
    -0.07
    èµı
    -0.07
    òi
    -0.07
    ãģ£ãģı
    -0.07
    ReuseIdentifier
    -0.07
    coni
    -0.07
    POSITIVE LOGITS
     again
    0.08
     became
    0.07
     become
    0.07
     accordingly
    0.07
     immediately
    0.07
     becomes
    0.07
     along
    0.07
    again
    0.06
     Become
    0.06
     Again
    0.06
    Activations Density 0.025%

    No Known Activations