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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4439
    Prev
    Next
    INDEX
    Explanations

    references to accidents and related terms

    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
    ABCDEFGHIJKLMNOP
    -0.08
    ãģªãĤī
    -0.08
       
    -0.07
    екÑģи
    -0.07
    ropa
    -0.06
    432
    -0.06
    ieber
    -0.06
    [...,
    -0.06
    anness
    -0.06
     ìŀIJë£Į
    -0.06
    POSITIVE LOGITS
     involving
    0.10
    /inc
    0.08
    aneous
    0.08
    æĢ§çļĦ
    0.08
    aly
    0.08
    ives
    0.07
    ive
    0.07
    ropolis
    0.07
    ly
    0.07
    antly
    0.07
    Activations Density 0.006%

    No Known Activations