Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125710
    Prev
    Next
    INDEX
    Explanations

    concepts related to waste management and disposal

    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
     Mundo
    -0.06
     Gloria
    -0.06
    Ñħа
    -0.06
     parl
    -0.06
    hana
    -0.06
    clc
    -0.06
     optics
    -0.06
     repr
    -0.06
     gl
    -0.06
     abs
    -0.06
    POSITIVE LOGITS
    Ïģκ
    0.07
    \CMS
    0.07
    ÑĢеÑĪ
    0.06
    iete
    0.06
    vie
    0.06
    ifa
    0.06
     oby
    0.06
    handleRequest
    0.06
    iasi
    0.06
    zes
    0.06
    Activations Density 0.007%

    No Known Activations