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. 5713
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity or collective terms

    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
    lett
    -0.07
    liest
    -0.07
    patches
    -0.07
    ÑĢиÑĤи
    -0.06
    Å¡tÄĽ
    -0.06
     anything
    -0.06
    ematik
    -0.06
    ilst
    -0.06
    ancies
    -0.06
     Jarvis
    -0.06
    POSITIVE LOGITS
     those
    0.10
     los
    0.09
     những
    0.08
    those
    0.08
    éĤ£äºĽ
    0.08
    ktop
    0.07
     les
    0.07
     ceux
    0.07
    Those
    0.07
     kinds
    0.07
    Activations Density 0.006%

    No Known Activations