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. 44141
    Prev
    Next
    INDEX
    Explanations

    references to the Chinese New Year

    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
    bjerg
    -0.08
    iola
    -0.07
    imeo
    -0.07
    andReturn
    -0.07
     granularity
    -0.07
    ãģĹãĤĩ
    -0.07
    olem
    -0.06
    _qs
    -0.06
    wargs
    -0.06
    CHED
    -0.06
    POSITIVE LOGITS
     festival
    0.10
     Festival
    0.09
     Year
    0.09
     Rat
    0.09
     Rabbit
    0.09
     festivities
    0.08
     Tiger
    0.08
     rabbit
    0.08
     celebration
    0.08
     celebrations
    0.08
    Activations Density 0.004%

    No Known Activations