© 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. 119368
    Prev
    Next
    INDEX
    Explanations

    references to Poland, particularly in relation to legal and humanitarian issues

    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
     Paginator
    -0.08
    Ãłi
    -0.07
    embre
    -0.07
    rana
    -0.07
    ÏģοÏįν
    -0.07
    778
    -0.07
    оÑĢе
    -0.06
    oter
    -0.06
     Needle
    -0.06
    ubat
    -0.06
    POSITIVE LOGITS
     indian
    0.06
    587
    0.06
    489
    0.06
     Roose
    0.06
    856
    0.05
    327
    0.05
     New
    0.05
     Welt
    0.05
     prima
    0.05
    íĨł
    0.05
    Activations Density 0.014%

    No Known Activations