© 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. 15-LLAMASCOPE-RES-131K
    11. 1119
    Prev
    Next
    INDEX
    Explanations

    phrases related to software processes and their control signals

    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
     ëĦ¤ìĿ´íĬ¸
    -0.08
    inking
    -0.07
    iddi
    -0.07
    egt
    -0.07
    yte
    -0.07
    ç»ĻæĪij
    -0.07
     Sabb
    -0.07
     \/
    -0.07
    oller
    -0.07
     lanc
    -0.06
    POSITIVE LOGITS
    borg
    0.07
     automatic
    0.06
     mole
    0.06
    ä¸įä¼ļ
    0.06
     Taste
    0.06
    bot
    0.06
    -visible
    0.06
     Presence
    0.06
    Ä°L
    0.06
    /latest
    0.06
    Activations Density 0.022%

    No Known Activations