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

    Neuronpedia

    Jacobian LensNEW
    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. 83043
    Prev
    Next
    INDEX
    Explanations

    discussions related to food safety and public health

    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
    _UNIQUE
    -0.07
     Classified
    -0.07
    ampoo
    -0.07
     Lý
    -0.06
     horr
    -0.06
    hb
    -0.06
     Mu
    -0.06
     eventually
    -0.06
    .BackgroundColor
    -0.06
    æ±Ĺ
    -0.06
    POSITIVE LOGITS
     Reaction
    0.10
     reaction
    0.10
     immediate
    0.09
     reactions
    0.09
     react
    0.09
    Reaction
    0.08
     immediately
    0.08
    React
    0.08
    dings
    0.07
     React
    0.07
    Activations Density 0.039%

    No Known Activations