© 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 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. 71195
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and geographical movements

    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
    .scalablytyped
    -0.08
    valuate
    -0.08
    inez
    -0.07
    itech
    -0.07
    WEBPACK
    -0.07
    earer
    -0.07
    indr
    -0.07
    ãģĨãģ¡
    -0.06
    âĸį
    -0.06
    AdapterManager
    -0.06
    POSITIVE LOGITS
     intermediary
    0.07
     intermedi
    0.06
     Holder
    0.06
     landmarks
    0.06
    through
    0.06
     through
    0.06
     via
    0.06
    0.06
     intermediate
    0.06
    Publication
    0.06
    Activations Density 0.026%

    No Known Activations