© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60130
    Prev
    Next
    INDEX
    Explanations

    references to restaurants and their details

    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
    oogle
    -0.07
    .si
    -0.06
    ibox
    -0.06
    apot
    -0.06
    jango
    -0.06
     maxlen
    -0.06
     Harvey
    -0.06
    ühr
    -0.06
    ková
    -0.06
     Jaune
    -0.06
    POSITIVE LOGITS
     franch
    0.09
     franchise
    0.07
    /hooks
    0.07
    æŀ¶
    0.07
     chains
    0.07
    Strip
    0.07
    chains
    0.07
     ÐijÑĸ
    0.07
     licensee
    0.07
    бÑĥÑĢг
    0.07
    Activations Density 0.009%

    No Known Activations