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. 11546
    Prev
    Next
    INDEX
    Explanations

    non-standard characters and symbols in the text

    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
    âĢį
    -0.07
    âĢĮâĢĮ
    -0.07
     “[
    -0.07
    —↵↵
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    ï¸
    -0.06
    ίο
    -0.06
     âĸĪâĸĪ
    -0.06
    ’Ñı
    -0.06
    ouz
    -0.06
    POSITIVE LOGITS
     --
    0.11
     NASCAR
    0.09
     Edwards
    0.08
     indeed
    0.08
     --↵
    0.08
    ..'
    0.08
     Daytona
    0.08
     ('
    0.07
    ....
    0.07
     Dover
    0.07
    Activations Density 0.003%

    No Known Activations