© 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. 82368
    Prev
    Next
    INDEX
    Explanations

    configurations and parameters related to server settings and network connections

    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
    eneg
    -0.07
    affen
    -0.07
    èĨľ
    -0.06
     naken
    -0.06
    cano
    -0.06
    +xml
    -0.06
    zman
    -0.06
    ubbo
    -0.06
    udo
    -0.06
    icorn
    -0.06
    POSITIVE LOGITS
     localhost
    0.13
    localhost
    0.13
    =localhost
    0.12
    127
    0.09
     host
    0.08
     local
    0.08
    host
    0.07
    IPAddress
    0.07
    local
    0.07
     sever
    0.07
    Activations Density 0.019%

    No Known Activations