© 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. 71806
    Prev
    Next
    INDEX
    Explanations

    mentions of military and political 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
    ibern
    -0.07
    itel
    -0.07
    ettes
    -0.07
    ľ
    -0.07
    SED
    -0.07
    Ïįν
    -0.07
    ABI
    -0.07
    ivas
    -0.07
    kiye
    -0.07
    λÏī
    -0.06
    POSITIVE LOGITS
    248
    0.07
    emp
    0.06
    pu
    0.06
     rede
    0.06
    zy
    0.06
    ardash
    0.06
     Proud
    0.06
     perman
    0.06
     advisers
    0.06
     footprint
    0.06
    Activations Density 0.026%

    No Known Activations