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. 43889
    Prev
    Next
    INDEX
    Explanations

    descriptors of characters and their appearances in various contexts

    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
    ÑĢиÑĤи
    -0.07
    iaux
    -0.07
    ilim
    -0.07
    chedulers
    -0.07
    RequestId
    -0.07
    itamin
    -0.07
    ypse
    -0.07
    ipeg
    -0.07
    NotFoundException
    -0.07
    Selectors
    -0.06
    POSITIVE LOGITS
     affected
    0.09
     affect
    0.08
     Chap
    0.08
     studied
    0.08
     affecting
    0.08
     aden
    0.08
     Bugs
    0.08
     saturn
    0.07
     donn
    0.07
    affected
    0.07
    Activations Density 0.049%

    No Known Activations