© 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. 85082
    Prev
    Next
    INDEX
    Explanations

    phrases expressing appreciation or excitement about travel recommendations

    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
    xis
    -0.06
    ixo
    -0.06
    counter
    -0.06
    вÑĸд
    -0.06
     counter
    -0.06
     OnTrigger
    -0.06
    readcr
    -0.06
     devote
    -0.06
    iday
    -0.05
    fund
    -0.05
    POSITIVE LOGITS
     Thanks
    0.08
     thank
    0.08
     thanks
    0.08
    thanks
    0.08
    Thanks
    0.08
     Thank
    0.08
     thanked
    0.08
    è°¢
    0.07
    ģm
    0.07
     dzi
    0.07
    Activations Density 0.020%

    No Known Activations