© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107104
    Prev
    Next
    INDEX
    Explanations

    references to people or entities that play a significant role or have influence in various contexts

    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
     porr
    -0.08
    ypi
    -0.07
    oto
    -0.07
    ioc
    -0.07
     ÑģоÑģÑĤ
    -0.07
    rite
    -0.06
    æł·åŃIJ
    -0.06
    ibel
    -0.06
    Ware
    -0.06
    меÑĩ
    -0.06
    POSITIVE LOGITS
     scenes
    0.10
     curtain
    0.10
     behind
    0.09
     Behind
    0.08
    -scenes
    0.08
    scenes
    0.08
     Scenes
    0.07
     veil
    0.07
     Curtain
    0.07
     Ùħباش
    0.07
    Activations Density 0.023%

    No Known Activations