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. 5695
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "of" in various contexts

    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
     Thousand
    -0.07
    ago
    -0.07
    AGO
    -0.07
     Weiss
    -0.07
    ollapsed
    -0.07
     Stark
    -0.06
    bout
    -0.06
    kowski
    -0.06
    одеÑĢж
    -0.06
     chaud
    -0.06
    POSITIVE LOGITS
    sted
    0.09
    ¦y
    0.07
    oin
    0.07
    perty
    0.07
     Kend
    0.07
    imizer
    0.07
    ún
    0.07
    croft
    0.07
    ragen
    0.06
    ENE
    0.06
    Activations Density 0.027%

    No Known Activations