© 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. 3983
    Prev
    Next
    INDEX
    Explanations

    mentions of actions related to opening new tabs or windows

    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
    illet
    -0.07
    ocket
    -0.07
    alex
    -0.06
     ç¯
    -0.06
     Kore
    -0.06
    crm
    -0.06
    urgery
    -0.06
     Feng
    -0.06
    igner
    -0.06
    etro
    -0.06
    POSITIVE LOGITS
    agma
    0.09
    ÏĮÏģ
    0.07
    ãĤ·ãĥ¼
    0.07
    /swagger
    0.07
    ãĥ¼ãĥ³
    0.07
    Slf
    0.07
    _permalink
    0.06
    airs
    0.06
    PLUGIN
    0.06
    enler
    0.06
    Activations Density 0.002%

    No Known Activations