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. 5406
    Prev
    Next
    INDEX
    Explanations

    programming-related method and class references

    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
    OfType
    -0.07
     typeof
    -0.07
    rosse
    -0.06
     inverted
    -0.06
    rippling
    -0.06
     Tu
    -0.06
    ableView
    -0.06
    uture
    -0.06
    .community
    -0.06
     careers
    -0.06
    POSITIVE LOGITS
     assignable
    0.07
    Canonical
    0.07
     Burton
    0.07
    .newInstance
    0.07
    /interfaces
    0.07
    getSimpleName
    0.06
    Interfaces
    0.06
    quan
    0.06
    .interfaces
    0.06
    .getSimpleName
    0.06
    Activations Density 0.004%

    No Known Activations