© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84992
    Prev
    Next
    INDEX
    Explanations

    quantifiable measures related to performance or quality specifications

    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
    ëĿ¼ìĿ¸
    -0.07
     ECS
    -0.07
     suggestions
    -0.06
     ecs
    -0.06
    ConnectionFactory
    -0.06
     Giov
    -0.06
    é¦
    -0.06
    hed
    -0.06
    ween
    -0.06
    ãĥ¼ãĥ©
    -0.06
    POSITIVE LOGITS
     benefits
    0.07
     advantages
    0.07
    istik
    0.07
    astos
    0.07
     Benefits
    0.07
    aptured
    0.07
     users
    0.06
    olves
    0.06
    rega
    0.06
     Compared
    0.06
    Activations Density 0.045%

    No Known Activations