© 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. 61282
    Prev
    Next
    INDEX
    Explanations

    inquiries related to hotel logistics and guest 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
    jin
    -0.07
    à¸Ħล
    -0.06
    пÑĢав
    -0.06
    ;element
    -0.06
     punches
    -0.06
     sav
    -0.06
     Wilmington
    -0.06
    sak
    -0.06
     (?,
    -0.05
    ãĥĬãĥ«
    -0.05
    POSITIVE LOGITS
    adir
    0.07
    asl
    0.07
    uti
    0.06
    oppers
    0.06
    auses
    0.06
    ặn
    0.06
    AMS
    0.06
    emas
    0.06
    eref
    0.06
    rape
    0.06
    Activations Density 0.003%

    No Known Activations