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. 44230
    Prev
    Next
    INDEX
    Explanations

    architectural features and elements related to the layout of a home

    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
    Ñĥнк
    -0.07
    lod
    -0.06
     Ged
    -0.06
    رÙĪØ¯
    -0.06
    icast
    -0.06
    обов
    -0.06
    conc
    -0.06
     chung
    -0.06
     stricter
    -0.06
    Ø®Ùħ
    -0.06
    POSITIVE LOGITS
     flooding
    0.11
     flood
    0.11
     sliders
    0.10
     floods
    0.10
     sliding
    0.10
     French
    0.10
     folding
    0.10
     accordion
    0.09
     french
    0.09
     slider
    0.09
    Activations Density 0.018%

    No Known Activations