© 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. 125029
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and appreciation for creativity in design and craftsmanship

    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
     Ryder
    -0.06
    unch
    -0.06
    uÄį
    -0.06
     Shir
    -0.06
    ometr
    -0.06
    ude
    -0.05
     Padding
    -0.05
     Mou
    -0.05
    avan
    -0.05
    è°ĵ
    -0.05
    POSITIVE LOGITS
    rico
    0.07
    stoupil
    0.07
    amment
    0.07
     builder
    0.07
     forum
    0.07
    .finished
    0.07
     brethren
    0.07
     ï¼ļ
    0.07
     builders
    0.06
    /forum
    0.06
    Activations Density 0.054%

    No Known Activations