© 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. 129452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating numerical ratings or reviews

    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
     yourselves
    -0.06
    makt
    -0.06
    ide
    -0.06
    olk
    -0.06
     Sick
    -0.06
    ÏĥÏĦά
    -0.06
    tsx
    -0.06
    اصÙĦ
    -0.06
     vill
    -0.06
    hem
    -0.06
    POSITIVE LOGITS
    ανδ
    0.08
    ForResource
    0.07
    pulse
    0.07
    jÅ¡ÃŃ
    0.07
     pul
    0.07
    ì±ħ
    0.07
     Pulse
    0.07
    haar
    0.07
    zung
    0.07
    acci
    0.07
    Activations Density 0.001%

    No Known Activations