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. 43463
    Prev
    Next
    INDEX
    Explanations

    expressions of intensity and comparison

    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
     emin
    -0.09
     unten
    -0.08
     weiber
    -0.08
     invariably
    -0.08
     subsidi
    -0.07
     decidedly
    -0.07
     erst
    -0.07
     titten
    -0.07
    .MixedReality
    -0.07
     squarely
    -0.07
    POSITIVE LOGITS
     rel
    0.08
     informational
    0.08
     chill
    0.08
     dope
    0.07
     addict
    0.07
     hype
    0.07
     contradict
    0.07
    yy
    0.07
     relie
    0.07
     relate
    0.07
    Activations Density 0.051%

    No Known Activations