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. 5488
    Prev
    Next
    INDEX
    Explanations

    instances of communication and contact-related phrases

    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
    hurst
    -0.08
    æľĽ
    -0.07
    ary
    -0.07
    urst
    -0.06
    rum
    -0.06
     clone
    -0.06
    heid
    -0.06
    ilog
    -0.06
    ummings
    -0.06
     Clone
    -0.06
    POSITIVE LOGITS
     us
    0.10
     directly
    0.07
     Us
    0.07
     me
    0.07
    -us
    0.07
    æĨ
    0.07
     anytime
    0.06
    管çIJĨåijĺ
    0.06
    ús
    0.06
    shint
    0.06
    Activations Density 0.010%

    No Known Activations