© 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. 56361
    Prev
    Next
    INDEX
    Explanations

    statistics related to health, economic conditions, or market trends

    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
    ãĤº
    -0.08
    ponse
    -0.07
    opleft
    -0.07
    oldt
    -0.07
    æ·
    -0.07
    riott
    -0.07
    /Foundation
    -0.07
    ÙĪجÙĪد
    -0.07
    ůr
    -0.07
     Blasio
    -0.07
    POSITIVE LOGITS
     Specialist
    0.06
    ellen
    0.06
    asso
    0.06
    l
    0.06
    aju
    0.06
    ysi
    0.06
    r
    0.05
    isa
    0.05
     defe
    0.05
    616
    0.05
    Activations Density 0.038%

    No Known Activations