© 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. 94388
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or contrasts between entities

    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
     nice
    -0.06
     sharp
    -0.06
     bruk
    -0.06
     Ward
    -0.06
    ute
    -0.06
    stry
    -0.05
    kov
    -0.05
     weakest
    -0.05
     nicely
    -0.05
     shortest
    -0.05
    POSITIVE LOGITS
     more
    0.14
    æĽ´
    0.11
    æĽ´å¤ļ
    0.11
    æĽ´åĬł
    0.10
    more
    0.10
     æĽ´
    0.10
     lebih
    0.10
    -more
    0.09
     ÏĢιο
    0.09
     más
    0.09
    Activations Density 0.053%

    No Known Activations