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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4552
    Prev
    Next
    INDEX
    Explanations

    conjunctions that link descriptions of creativity and artistic styles

    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
    omid
    -0.07
     studies
    -0.07
     studi
    -0.06
     Rag
    -0.06
     Studies
    -0.06
    Studies
    -0.06
    anted
    -0.06
     students
    -0.06
    æ°ı
    -0.06
     study
    -0.05
    POSITIVE LOGITS
    azel
    0.07
    _IOC
    0.07
     grace
    0.07
    ilim
    0.07
     Nations
    0.07
    koa
    0.07
     Trends
    0.07
     manner
    0.07
    hab
    0.07
    ERSION
    0.06
    Activations Density 0.011%

    No Known Activations