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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40709
    Prev
    Next
    INDEX
    Explanations

    complex sentences and their structures

    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
     sharp
    -0.07
    ãģĻãģĻ
    -0.07
    ucci
    -0.07
    andre
    -0.06
    _SAFE
    -0.06
     sharpen
    -0.06
    оÑģоб
    -0.06
    118
    -0.06
    urrect
    -0.06
     shorthand
    -0.06
    POSITIVE LOGITS
     fewer
    0.15
     differently
    0.15
     less
    0.14
    ãģĵãģ¡ãĤī
    0.13
     weniger
    0.13
     meno
    0.12
     similarly
    0.11
     more
    0.11
     menos
    0.11
     moins
    0.11
    Activations Density 0.146%

    No Known Activations