© 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. 57480
    Prev
    Next
    INDEX
    Explanations

    references to military logistics and challenges

    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
    eli
    -0.07
    ç½
    -0.06
     SWAT
    -0.06
    avig
    -0.06
    åĥı
    -0.06
     ÑĤеÑĩ
    -0.06
    chw
    -0.06
     steer
    -0.06
     Navigator
    -0.06
    iegel
    -0.06
    POSITIVE LOGITS
    soon
    0.08
    eway
    0.07
    atre
    0.07
    оÑĤо
    0.06
    ónico
    0.06
    askell
    0.06
    à¥Ģप
    0.06
    thal
    0.06
    poon
    0.06
     sond
    0.06
    Activations Density 0.031%

    No Known Activations