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. 43718
    Prev
    Next
    INDEX
    Explanations

    references to comedic content and its popularity

    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
     addCriterion
    -0.08
    aden
    -0.07
     rehears
    -0.07
    ester
    -0.07
    ancellable
    -0.07
    whereIn
    -0.07
    PropertyChanged
    -0.07
    raz
    -0.07
    asmus
    -0.07
    apse
    -0.07
    POSITIVE LOGITS
     mel
    0.09
     melody
    0.07
     discharge
    0.07
     deliveries
    0.07
     delivery
    0.07
     discharged
    0.07
     spilled
    0.07
     delivering
    0.06
     collection
    0.06
     account
    0.06
    Activations Density 0.004%

    No Known Activations