© 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. 126615
    Prev
    Next
    INDEX
    Explanations

    instances of unexpected events and discoveries

    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
     Zem
    -0.07
    Tube
    -0.07
    XL
    -0.07
    anz
    -0.07
     ÙĨظر
    -0.07
    allo
    -0.06
    Fatal
    -0.06
    даеÑĤÑģÑı
    -0.06
    жи
    -0.06
     Spicer
    -0.06
    POSITIVE LOGITS
     Patch
    0.07
     blank
    0.06
     a
    0.06
    gow
    0.06
     bol
    0.06
     reb
    0.06
     foot
    0.06
     patch
    0.06
    akis
    0.06
    pack
    0.06
    Activations Density 0.007%

    No Known Activations