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. 5469
    Prev
    Next
    INDEX
    Explanations

    phrases that assess or describe quality and value in a context

    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
    usz
    -0.06
     Pearce
    -0.06
    Entities
    -0.06
    misc
    -0.06
    fo
    -0.06
    ws
    -0.05
    анов
    -0.05
    à¸ļล
    -0.05
    Ease
    -0.05
     ws
    -0.05
    POSITIVE LOGITS
     way
    0.10
     ways
    0.08
     GOOD
    0.08
    -way
    0.07
     good
    0.07
     Way
    0.07
    WAY
    0.07
    way
    0.07
     kind
    0.07
    wdx
    0.07
    Activations Density 0.012%

    No Known Activations