Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60964
    Prev
    Next
    INDEX
    Explanations

    instances of the word "short" and its related phrases or contexts

    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
    ishi
    -0.08
    iske
    -0.08
    жен
    -0.07
    bsite
    -0.07
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    -0.07
     ØŃÚ©Ùħ
    -0.07
    лоп
    -0.07
    apl
    -0.06
    há
    -0.06
    chine
    -0.06
    POSITIVE LOGITS
     expectations
    0.07
    /full
    0.07
    .hs
    0.06
    ontent
    0.06
    LL
    0.06
    //{{
    0.06
    oden
    0.06
    UNITY
    0.06
     expected
    0.06
    670
    0.06
    Activations Density 0.005%

    No Known Activations