© 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. 60696
    Prev
    Next
    INDEX
    Explanations

    references to online content management and feed systems

    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
     Snyder
    -0.06
    W
    -0.06
    ace
    -0.05
     Constitution
    -0.05
    403
    -0.05
    Warm
    -0.05
     apolog
    -0.05
    AYER
    -0.05
    ayer
    -0.05
    anted
    -0.05
    POSITIVE LOGITS
    ngine
    0.08
    bsd
    0.08
    ÙĪØ¯ÛĮ
    0.08
    è¡£
    0.08
    ecure
    0.08
    jezd
    0.07
    urent
    0.07
     @}
    0.07
    alars
    0.07
    hape
    0.07
    Activations Density 0.001%

    No Known Activations