© 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. 15-LLAMASCOPE-RES-131K
    6. 61505
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and assertions regarding potential breaches or issues

    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
    iÄĻ
    -0.08
    Å¡nÃŃ
    -0.07
    اÙĦÙī
    -0.07
    ServletContext
    -0.07
    REFERRED
    -0.07
    alue
    -0.07
    uem
    -0.07
    /Dk
    -0.07
    utc
    -0.07
    ibia
    -0.07
    POSITIVE LOGITS
     fore
    0.06
    upal
    0.06
     Lub
    0.05
     Muss
    0.05
     Palmer
    0.05
    areth
    0.05
    engu
    0.05
    [
    0.05
    gulp
    0.05
    179
    0.05
    Activations Density 0.019%

    No Known Activations