© 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. 22-LLAMASCOPE-RES-131K
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    topics related to the effectiveness and ethical implications of animal testing in research

    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
    ê·ł
    -0.06
     infection
    -0.06
    mant
    -0.06
     double
    -0.06
    ODO
    -0.06
    gis
    -0.06
     floats
    -0.06
    리ìĹIJ
    -0.05
    atron
    -0.05
     doubly
    -0.05
    POSITIVE LOGITS
    xic
    0.08
     dose
    0.08
     Safety
    0.08
     Toxic
    0.08
     Drug
    0.08
     safety
    0.08
    Tier
    0.08
    èĸ¬
    0.08
     drug
    0.08
     toxicity
    0.08
    Activations Density 0.011%

    No Known Activations