© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107346
    Prev
    Next
    INDEX
    Explanations

    mentions of cream and cheese ingredients

    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
    uggage
    -0.07
    adm
    -0.06
    quez
    -0.06
    rops
    -0.06
    cles
    -0.06
    OLS
    -0.06
    uty
    -0.06
     trái
    -0.06
     baÄŁ
    -0.06
    gings
    -0.06
    POSITIVE LOGITS
    ery
    0.09
    onian
    0.08
    erton
    0.08
    iness
    0.08
    iest
    0.08
    ERY
    0.08
    ier
    0.07
    IER
    0.07
    obile
    0.07
    buffers
    0.07
    Activations Density 0.007%

    No Known Activations