© 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. 71388
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing states or actions

    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
     still
    -0.13
    still
    -0.12
     Still
    -0.12
     STILL
    -0.11
    Still
    -0.10
     ancora
    -0.10
     again
    -0.09
     ainda
    -0.09
     ìķĦì§ģ
    -0.09
    again
    -0.09
    POSITIVE LOGITS
    ora
    0.06
     mono
    0.06
    оÑĢа
    0.06
    aland
    0.06
    ODO
    0.06
    ļĮ
    0.06
    elor
    0.06
    gar
    0.06
    à¸Ļà¸Ļ
    0.06
    ldr
    0.05
    Activations Density 0.006%

    No Known Activations