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. 5731
    Prev
    Next
    INDEX
    Explanations

    specific names of athletes and sports-related terms

    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
    _vlog
    -0.08
    .ibm
    -0.08
    cak
    -0.08
    oningen
    -0.08
    ellido
    -0.07
    noch
    -0.07
    hap
    -0.07
    using
    -0.07
    Intialized
    -0.07
    /**č↵
    -0.07
    POSITIVE LOGITS
     another
    0.10
     Speaking
    0.10
     speaking
    0.10
     maybe
    0.09
     probably
    0.09
     ok
    0.09
     if
    0.09
     Another
    0.09
    Speaking
    0.08
     If
    0.08
    Activations Density 0.025%

    No Known Activations