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. 5577
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "click here for" indicating links or calls to action

    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
    ÙģÙĨ
    -0.07
    æ´
    -0.06
    اÛĮÙĩ
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
     vamp
    -0.06
    verbosity
    -0.06
     mÃŃt
    -0.06
    845
    -0.06
    edicine
    -0.06
     HoÃłng
    -0.06
    POSITIVE LOGITS
     more
    0.09
     full
    0.08
     details
    0.08
     link
    0.08
    æĽ´å¤ļ
    0.08
     larger
    0.08
     access
    0.07
     instructions
    0.07
    Link
    0.07
     latest
    0.07
    Activations Density 0.008%

    No Known Activations