© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60843
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions related to recipes

    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
    ikip
    -0.08
    istrat
    -0.08
     resourceName
    -0.08
    KANJI
    -0.08
    adolu
    -0.08
    .snap
    -0.08
    kili
    -0.08
    /testify
    -0.08
    elay
    -0.07
    .usermodel
    -0.07
    POSITIVE LOGITS
     salt
    0.09
     Salt
    0.08
    Salt
    0.07
     taste
    0.06
     bay
    0.06
     liberal
    0.06
     garlic
    0.06
     Drain
    0.06
    uma
    0.06
    0.06
    Activations Density 0.124%

    No Known Activations