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. 31-LLAMASCOPE-RES-131K
    6. 43564
    Prev
    Next
    INDEX
    Explanations

    references to economic impacts and inequalities related to education and digital access

    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
    yster
    -0.07
    elmet
    -0.06
    kuk
    -0.06
    652
    -0.06
    御
    -0.06
     bothered
    -0.06
     invaded
    -0.06
    agua
    -0.06
    ucha
    -0.06
    uze
    -0.06
    POSITIVE LOGITS
     missed
    0.10
     widening
    0.09
     lost
    0.09
     regression
    0.09
     reg
    0.08
     exclusion
    0.08
     hollow
    0.08
     stagn
    0.08
     missing
    0.08
     regress
    0.08
    Activations Density 0.060%

    No Known Activations