© 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. 17-LLAMASCOPE-RES-131K
    11. 16519
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements

    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
    isu
    -0.07
    arge
    -0.06
    +-
    -0.06
    ifest
    -0.06
    STRACT
    -0.06
     spit
    -0.05
    ada
    -0.05
    åĵ
    -0.05
    дел
    -0.05
    del
    -0.05
    POSITIVE LOGITS
     anyone
    0.13
     anybody
    0.12
     Anyone
    0.10
    Anyone
    0.10
    aç
    0.08
    Interested
    0.07
    eyin
    0.07
     Interested
    0.07
    ldb
    0.07
     interested
    0.07
    Activations Density 0.018%

    No Known Activations