© 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. 15-LLAMASCOPE-RES-131K
    6. 26827
    Prev
    Next
    INDEX
    Explanations

    commands related to setting up and managing authentication for email servers

    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
    Ñı
    -0.06
    ansa
    -0.06
    rink
    -0.06
    /navigation
    -0.06
    uan
    -0.06
    аÑĢан
    -0.05
     Eight
    -0.05
    ÏħÏĢ
    -0.05
    anuts
    -0.05
    lation
    -0.05
    POSITIVE LOGITS
    ÏĥÏĥα
    0.07
    κÏģα
    0.07
    ÏĥοÏħ
    0.07
    .mods
    0.07
    ega
    0.07
    तर
    0.07
    enthal
    0.07
    eger
    0.07
     fon
    0.06
    å¡ļ
    0.06
    Activations Density 0.171%

    No Known Activations