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. 44074
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and characters

    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
     somebody
    -0.07
     maybe
    -0.06
     anybody
    -0.06
     anyways
    -0.06
    maybe
    -0.06
    ëĿ¼ëıĦ
    -0.05
     explicitly
    -0.05
    olik
    -0.05
    íļĮìĿĺ
    -0.05
    orra
    -0.05
    POSITIVE LOGITS
     bride
    0.12
     brides
    0.10
     wedding
    0.10
     escorted
    0.09
     grandparents
    0.09
     bridal
    0.09
     Bride
    0.09
     Wedding
    0.09
     groom
    0.08
     maid
    0.08
    Activations Density 0.006%

    No Known Activations