© 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. 22-LLAMASCOPE-RES-131K
    6. 3727
    Prev
    Next
    INDEX
    Explanations

    comparisons and rankings of candy or snack options

    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
    ihat
    -0.07
     bread
    -0.07
     Bread
    -0.06
    umber
    -0.06
    ilter
    -0.06
     potatoes
    -0.06
    ToFit
    -0.06
    efore
    -0.06
    ilters
    -0.05
    ton
    -0.05
    POSITIVE LOGITS
     candy
    0.10
     candies
    0.10
     chew
    0.10
     Gum
    0.08
     Trident
    0.08
     nou
    0.08
    kola
    0.08
    ç³ĸ
    0.08
    umd
    0.07
     gum
    0.07
    Activations Density 0.024%

    No Known Activations