Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43951
    Prev
    Next
    INDEX
    Explanations

    elements related to transportation and travel logistics

    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
    ãĥ³ãĤ¸
    -0.07
    /sidebar
    -0.07
    formace
    -0.07
     Wik
    -0.06
     Ensemble
    -0.06
    adoo
    -0.06
    èĬĿ
    -0.06
    annes
    -0.06
    canf
    -0.06
    datagrid
    -0.06
    POSITIVE LOGITS
     bus
    0.18
     buses
    0.16
     Bus
    0.15
    Bus
    0.14
    bus
    0.13
     Volvo
    0.13
     BUS
    0.12
    _bus
    0.12
    .bus
    0.12
    ãĥIJãĤ¹
    0.11
    Activations Density 0.005%

    No Known Activations