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. 43933
    Prev
    Next
    INDEX
    Explanations

    phrases related to gameplay mechanics and in-game experiences

    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
    voke
    -0.07
    ãĥ³ãĤº
    -0.06
    mapper
    -0.06
     superst
    -0.06
    dni
    -0.06
    ä¼łå¥ĩ
    -0.06
     BOOT
    -0.06
    声ãĤĴ
    -0.06
     Dün
    -0.06
     ÑģлÑĥÑħ
    -0.06
    POSITIVE LOGITS
     explosions
    0.10
     CGI
    0.09
     pursued
    0.09
     exploding
    0.09
    plode
    0.08
     buildings
    0.08
     lasers
    0.08
     cgi
    0.08
     explode
    0.08
     skys
    0.08
    Activations Density 0.025%

    No Known Activations