© 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. 129825
    Prev
    Next
    INDEX
    Explanations

    references to different types of insurance and coverage options

    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
    okoj
    -0.07
    rex
    -0.07
    kÄĻ
    -0.07
    anagan
    -0.06
    abouts
    -0.06
    PEAT
    -0.06
    etes
    -0.06
    dup
    -0.06
     ë²
    -0.06
    ÑĮÑı
    -0.06
    POSITIVE LOGITS
    ior
    0.07
    CompanyId
    0.06
    SCO
    0.06
     Pearce
    0.06
    374
    0.06
    indre
    0.06
    andaÅŁ
    0.06
    idence
    0.06
    olina
    0.06
    sti
    0.06
    Activations Density 0.002%

    No Known Activations