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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28571
    Prev
    Next
    INDEX
    Explanations

    references to warnings or alerts about potential dangers or crises

    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
    864
    -0.06
    asar
    -0.06
     Scout
    -0.06
     Splash
    -0.06
    och
    -0.05
    doi
    -0.05
     пÑĢеÑģ
    -0.05
    x
    -0.05
    oret
    -0.05
     doi
    -0.05
    POSITIVE LOGITS
     Bilder
    0.09
     truth
    0.08
    -BEGIN
    0.08
    truth
    0.08
    #
    0.08
    ouver
    0.07
    Truth
    0.07
    PFN
    0.07
    ajes
    0.07
    -ln
    0.07
    Activations Density 0.085%

    No Known Activations