© 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. 82199
    Prev
    Next
    INDEX
    Explanations

    personal reflections and expressions of individual experiences

    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
    isse
    -0.08
    wy
    -0.06
    orman
    -0.06
    ypress
    -0.06
    wan
    -0.06
    lse
    -0.06
    wall
    -0.06
     Malik
    -0.06
    ruk
    -0.06
    duk
    -0.06
    POSITIVE LOGITS
     personally
    0.13
     personal
    0.09
     Personally
    0.08
     Personal
    0.07
    Personal
    0.07
    personal
    0.07
    Personally
    0.06
    æĿ¥è¯´
    0.06
     à¹Ĩ
    0.06
    ÑĥÑĤÑĮ
    0.06
    Activations Density 0.012%

    No Known Activations