© 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. 87726
    Prev
    Next
    INDEX
    Explanations

    terms related to boundaries or connections within a varying 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
    ëĵĿ
    -0.06
    XD
    -0.06
    uzz
    -0.06
     ÑĢазви
    -0.06
    iche
    -0.06
    oxetine
    -0.06
     Kund
    -0.06
    ëĭ¹
    -0.06
    side
    -0.06
    ewise
    -0.06
    POSITIVE LOGITS
    наÑĢод
    0.09
    nar
    0.07
    ilet
    0.07
    ylül
    0.06
    ingers
    0.06
     Fry
    0.06
    ÄŁer
    0.06
    inalg
    0.06
     Fol
    0.06
    stal
    0.06
    Activations Density 0.001%

    No Known Activations