© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97952
    Prev
    Next
    INDEX
    Explanations

    specific dates and references to military operations

    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
    orget
    -0.07
    è¦ļ
    -0.07
     Kiss
    -0.07
    евид
    -0.07
    ternet
    -0.07
    ollectors
    -0.07
    Disappear
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    rex
    -0.07
    esson
    -0.07
    POSITIVE LOGITS
    tom
    0.06
    A
    0.06
    4
    0.06
    jay
    0.06
    aff
    0.06
    feld
    0.05
    B
    0.05
    HT
    0.05
    annes
    0.05
    3
    0.05
    Activations Density 0.035%

    No Known Activations