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. 5478
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to infrastructure projects and their evaluations

    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
    616
    -0.06
    Âİ
    -0.06
    ichen
    -0.06
     surplus
    -0.06
     couple
    -0.05
    061
    -0.05
    UPLE
    -0.05
    053
    -0.05
    dg
    -0.05
     getattr
    -0.05
    POSITIVE LOGITS
     $
    0.15
     project
    0.14
     £
    0.13
    project
    0.12
    -project
    0.12
     projects
    0.11
     Project
    0.11
     projectId
    0.11
     proj
    0.11
     controversial
    0.11
    Activations Density 0.035%

    No Known Activations