© 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. 76645
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment relating to food and dining 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
    ining
    -0.07
    axon
    -0.06
     cigaret
    -0.06
    znik
    -0.06
    \db
    -0.06
    Shift
    -0.06
    prot
    -0.06
    uger
    -0.06
     stocking
    -0.06
     Protector
    -0.06
    POSITIVE LOGITS
     Mara
    0.07
     mouth
    0.07
    lichkeit
    0.06
    =file
    0.06
    igli
    0.06
     isot
    0.06
    Ø´Ùĩ
    0.06
    лÑıв
    0.06
     DISCLAIM
    0.06
    ioneer
    0.06
    Activations Density 0.016%

    No Known Activations