© 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. 15-LLAMASCOPE-RES-131K
    11. 61844
    Prev
    Next
    INDEX
    Explanations

    terms related to food safety and health risks

    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
    aney
    -0.07
    bomb
    -0.07
    .TabIndex
    -0.07
    หม
    -0.07
    andes
    -0.07
     Bros
    -0.07
     rtrim
    -0.06
    à¸Ĭà¸Ļ
    -0.06
    cede
    -0.06
    497
    -0.06
    POSITIVE LOGITS
     traced
    0.06
     microbial
    0.06
     van
    0.06
     safety
    0.06
    elve
    0.06
     Legion
    0.06
    iliary
    0.06
    utterstock
    0.06
    ackers
    0.06
     Camp
    0.06
    Activations Density 0.040%

    No Known Activations