© 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. 15-LLAMASCOPE-RES-131K
    11. 26959
    Prev
    Next
    INDEX
    Explanations

    specific references to authors or contributors in a publication context

    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
    Äįet
    -0.07
    istan
    -0.06
    ÑĢоÑģÑĤо
    -0.06
     æ°¸
    -0.06
    zell
    -0.06
    758
    -0.06
    okoj
    -0.06
    販
    -0.06
    isme
    -0.06
     Spicer
    -0.06
    POSITIVE LOGITS
    tü
    0.06
    åºľ
    0.06
    düm
    0.06
    _excerpt
    0.06
     TypeInfo
    0.06
    ewan
    0.06
    .Scene
    0.06
    .UIManager
    0.06
    tran
    0.06
    berger
    0.06
    Activations Density 0.154%

    No Known Activations