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. 5623
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or passion

    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
    vez
    -0.07
    urge
    -0.07
    yonel
    -0.07
    .PerformLayout
    -0.07
    ामà¤ķ
    -0.07
    ual
    -0.07
    canf
    -0.07
    itized
    -0.07
    .UnitTesting
    -0.07
     jadx
    -0.07
    POSITIVE LOGITS
     detail
    0.08
    /lo
    0.08
     Detail
    0.07
     anything
    0.07
    Detail
    0.07
     science
    0.07
    orraine
    0.06
     everything
    0.06
     adventure
    0.06
     certain
    0.06
    Activations Density 0.038%

    No Known Activations