© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75674
    Prev
    Next
    INDEX
    Explanations

    references to personal favorites or preferences in culture, literature, and entertainment

    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
    offer
    -0.07
    creativecommons
    -0.07
    ãĥĨãĥ«
    -0.07
    tright
    -0.06
     offer
    -0.06
    abble
    -0.06
     upside
    -0.06
    idor
    -0.06
     norms
    -0.06
    yle
    -0.06
    POSITIVE LOGITS
     favorite
    0.13
     favorites
    0.12
     Favorite
    0.11
     favourite
    0.11
    favorite
    0.10
     favourites
    0.10
    Favorite
    0.09
    .favorite
    0.08
     Favor
    0.08
    avorite
    0.08
    Activations Density 0.066%

    No Known Activations