© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77331
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the performance and functionality of a coffee-making machine

    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
    estre
    -0.09
     Gest
    -0.07
    baugh
    -0.06
     mat
    -0.06
    ephir
    -0.06
    (ed
    -0.06
    etas
    -0.06
    ÃŃch
    -0.06
    ango
    -0.06
     aure
    -0.06
    POSITIVE LOGITS
     mode
    0.17
     modes
    0.15
     Mode
    0.15
    Mode
    0.14
    mode
    0.13
    -mode
    0.13
     Modes
    0.13
    模å¼ı
    0.13
    _mode
    0.12
    modes
    0.12
    Activations Density 0.044%

    No Known Activations