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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29650
    Prev
    Next
    INDEX
    Explanations

    references to events or actions related to transportation or travel

    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
     kolo
    -0.08
    leston
    -0.07
    ancell
    -0.07
    037
    -0.07
    elsea
    -0.07
    ÑĨей
    -0.07
    enger
    -0.06
    mods
    -0.06
    deaux
    -0.06
    upal
    -0.06
    POSITIVE LOGITS
     from
    0.07
    ogan
    0.07
    arp
    0.07
    =start
    0.07
     khợi
    0.07
    departure
    0.06
     start
    0.06
    -start
    0.06
    nings
    0.06
     partir
    0.06
    Activations Density 0.033%

    No Known Activations