© 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. 3143
    Prev
    Next
    INDEX
    Explanations

    references to conferences and formal gatherings

    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
    ertest
    -0.07
    haf
    -0.06
    uat
    -0.06
     Interview
    -0.06
    ober
    -0.06
    è¾ŀ
    -0.06
    .navigationItem
    -0.06
    usercontent
    -0.06
     gyr
    -0.06
    ONA
    -0.06
    POSITIVE LOGITS
     conference
    0.08
    _sym
    0.08
    held
    0.07
    cul
    0.07
    Themes
    0.07
    conference
    0.07
     IIC
    0.07
     конÑĦеÑĢен
    0.07
     hosted
    0.07
    -theme
    0.07
    Activations Density 0.027%

    No Known Activations