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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 38788
    Prev
    Next
    INDEX
    Explanations

    travel-related phrases and destinations

    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
    tern
    -0.08
    ollo
    -0.07
    #__
    -0.07
    opleft
    -0.07
    annel
    -0.07
    åŃĺäºİ
    -0.07
     gam
    -0.07
    ãģ¯ãģļ
    -0.07
    è´¹
    -0.07
    .Quad
    -0.07
    POSITIVE LOGITS
     destinations
    0.07
    alim
    0.07
     destination
    0.06
    agy
    0.06
     unreachable
    0.06
    K
    0.06
    pageTitle
    0.05
     temperatures
    0.05
    dale
    0.05
     Kup
    0.05
    Activations Density 0.004%

    No Known Activations