© 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. 83683
    Prev
    Next
    INDEX
    Explanations

    discussions about the limitations of animal testing in relation to human health outcomes

    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
    oller
    -0.09
    serrat
    -0.07
    elix
    -0.06
    оÑĩка
    -0.06
    land
    -0.06
    -pos
    -0.06
    ç¯Ģ
    -0.06
    976
    -0.06
    (strpos
    -0.06
     narr
    -0.06
    POSITIVE LOGITS
     representative
    0.16
    代表
    0.13
     representing
    0.12
     represent
    0.12
     represents
    0.12
    represent
    0.11
     Representative
    0.11
     representatives
    0.11
     representa
    0.10
     REPRESENT
    0.10
    Activations Density 0.056%

    No Known Activations