Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5361
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their match schedules

    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
     Soon
    -0.08
    té
    -0.07
    <typeof
    -0.07
     soon
    -0.07
    soon
    -0.07
    xit
    -0.07
    Incoming
    -0.07
    ena
    -0.07
    onne
    -0.07
    Soon
    -0.07
    POSITIVE LOGITS
     travel
    0.07
     Tuesday
    0.06
    ptime
    0.06
    awa
    0.06
     JV
    0.06
     homework
    0.06
     HOME
    0.06
    ermen
    0.06
    abra
    0.06
     scheduled
    0.06
    Activations Density 0.021%

    No Known Activations