© 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. 16721
    Prev
    Next
    INDEX
    Explanations

    references or definitions of terms and concepts

    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
    γοÏħ
    -0.07
    çIJĨçĶ±
    -0.06
    ystack
    -0.06
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.06
    ลา
    -0.06
    woo
    -0.06
    ách
    -0.06
     ìŀĪëĭ¤ê³ł
    -0.06
    ishops
    -0.06
    616
    -0.06
    POSITIVE LOGITS
    çļĦæĺ¯
    0.08
    ä¸Ģç§į
    0.06
     Ñģобой
    0.06
    484
    0.06
    557
    0.06
    avl
    0.06
    izes
    0.06
    PPER
    0.06
    909
    0.06
     lin
    0.06
    Activations Density 0.007%

    No Known Activations