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. 44195
    Prev
    Next
    INDEX
    Explanations

    sentences that address various types of furniture or design-related topics

    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
     id
    -0.07
     not
    -0.07
     n
    -0.07
     res
    -0.07
     text
    -0.06
     this
    -0.06
     super
    -0.06
     other
    -0.06
     re
    -0.06
     well
    -0.06
    POSITIVE LOGITS
    gebn
    0.09
     Filename
    0.09
    impse
    0.09
     pÅĻip
    0.09
    rowser
    0.08
    нообÑĢаз
    0.08
    _mD
    0.08
    InnerHTML
    0.08
    InternalServerError
    0.08
    SplitOptions
    0.08
    Activations Density 0.002%

    No Known Activations