© 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. 29856
    Prev
    Next
    INDEX
    Explanations

    historical dates and significant periods related to warfare

    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
    MOVED
    -0.07
    erea
    -0.06
    &P
    -0.06
    خاÙĨ
    -0.06
    isible
    -0.06
    ané
    -0.06
    ammable
    -0.06
    ivan
    -0.06
    yw
    -0.06
    nown
    -0.06
    POSITIVE LOGITS
     Revel
    0.07
    uel
    0.07
    .deb
    0.06
    ãĥ¬ãĤ¹
    0.06
    rov
    0.06
    วà¸ģ
    0.06
    mî
    0.06
     ogl
    0.06
    ÑĸÑĶ
    0.06
     completing
    0.06
    Activations Density 0.021%

    No Known Activations