© 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. 82206
    Prev
    Next
    INDEX
    Explanations

    discussions about errors and their consequences in processes or practices

    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
    å¥
    -0.07
    uft
    -0.07
     رÙħ
    -0.06
    377
    -0.06
    беÑĢ
    -0.06
    аÑĤков
    -0.06
    WARN
    -0.06
    uting
    -0.06
    ')?>
    -0.06
    каж
    -0.06
    POSITIVE LOGITS
     entire
    0.10
     whole
    0.08
    æķ´ä¸ª
    0.08
     Entire
    0.07
     instantly
    0.07
     Whole
    0.07
     consequences
    0.07
    Whole
    0.07
    ëĿ½
    0.07
     instant
    0.07
    Activations Density 0.021%

    No Known Activations