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. 44043
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to mathematical or scientific concepts

    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
     fucking
    -0.11
     Fucking
    -0.11
     Fuck
    -0.10
     fuck
    -0.09
    Fuck
    -0.09
    fuck
    -0.09
     FUCK
    -0.09
     shit
    -0.08
     fucks
    -0.08
     Literature
    -0.08
    POSITIVE LOGITS
     teens
    0.10
     teen
    0.09
     teenagers
    0.09
     kids
    0.09
     Teen
    0.08
     agent
    0.08
     tween
    0.08
     Teens
    0.08
     agents
    0.08
     kid
    0.07
    Activations Density 0.006%

    No Known Activations