© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88872
    Prev
    Next
    INDEX
    Explanations

    specific historical events or figures related to conflicts and 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
    sortable
    -0.08
    ordum
    -0.07
    rame
    -0.07
    vail
    -0.07
    utzer
    -0.07
    pector
    -0.07
    letic
    -0.07
    ording
    -0.07
    IBE
    -0.07
    eroon
    -0.07
    POSITIVE LOGITS
    281
    0.06
     powder
    0.06
    eus
    0.06
    交
    0.06
    alc
    0.06
     Harley
    0.06
    å®Ĺ
    0.06
    SCAN
    0.06
     principal
    0.05
     Principal
    0.05
    Activations Density 0.061%

    No Known Activations