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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5517
    Prev
    Next
    INDEX
    Explanations

    phrases that express opportunities or chances

    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
    roups
    -0.07
    roup
    -0.07
    .IsSuccess
    -0.07
    ói
    -0.07
    STER
    -0.07
    .getSharedPreferences
    -0.06
     culo
    -0.06
    _KEEP
    -0.06
    /owl
    -0.06
    obi
    -0.06
    POSITIVE LOGITS
     opportunity
    0.62
     chance
    0.55
     opportunities
    0.47
     Opportunity
    0.44
    æľºä¼ļ
    0.43
     Chance
    0.41
     oportun
    0.40
    Chance
    0.38
     Opportunities
    0.37
     chances
    0.35
    Activations Density 0.221%

    No Known Activations