© 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. 15-LLAMASCOPE-RES-131K
    11. 89360
    Prev
    Next
    INDEX
    Explanations

    keywords related to travel and tourism-related 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
    á»ĵ
    -0.07
    âĻĢ
    -0.07
    ransition
    -0.07
    enburg
    -0.06
    riday
    -0.06
    ervo
    -0.06
    Ïģε
    -0.06
    fell
    -0.06
    hev
    -0.06
    samp
    -0.06
    POSITIVE LOGITS
     Wings
    0.08
    enze
    0.06
    lobal
    0.06
    orch
    0.06
    fly
    0.06
     unb
    0.06
     Fly
    0.06
     Gat
    0.06
    AINS
    0.06
    èħ¹
    0.06
    Activations Density 0.008%

    No Known Activations