© 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. 5321
    Prev
    Next
    INDEX
    Explanations

    references to transportation options and travel information

    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
    azz
    -0.08
    mere
    -0.07
    ree
    -0.07
    terra
    -0.07
    artz
    -0.07
     DÃŃky
    -0.07
    عÙĦÛĮ
    -0.07
    UBE
    -0.07
     вÑģего
    -0.07
    ango
    -0.06
    POSITIVE LOGITS
    bis
    0.07
    -clock
    0.06
     veget
    0.06
    anian
    0.06
     Dro
    0.06
    andon
    0.06
     Tent
    0.05
     Otto
    0.05
    utton
    0.05
    ision
    0.05
    Activations Density 0.012%

    No Known Activations