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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75341
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of hotel facilities and services

    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
    odash
    -0.07
    naire
    -0.07
    ós
    -0.06
     chặt
    -0.06
    еÑĢб
    -0.06
    IFEST
    -0.06
    imdi
    -0.06
     booths
    -0.06
     Manifest
    -0.06
    ÏģÏĮÏĤ
    -0.06
    POSITIVE LOGITS
    unger
    0.07
     internet
    0.07
    éīĦ
    0.07
     Hess
    0.07
    orr
    0.06
     facilities
    0.06
     Internet
    0.06
    Invariant
    0.06
    ovit
    0.06
     laundry
    0.06
    Activations Density 0.022%

    No Known Activations