© 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. 71972
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and formatting symbols

    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
    reh
    -0.07
    rei
    -0.07
    .protobuf
    -0.07
    zer
    -0.06
    479
    -0.06
    arov
    -0.06
     Mansion
    -0.06
    orra
    -0.06
    ologne
    -0.06
     srd
    -0.06
    POSITIVE LOGITS
    swing
    0.06
    istr
    0.06
     lp
    0.06
     Fay
    0.06
    ISTR
    0.06
     Swing
    0.06
    ASSES
    0.06
    lag
    0.05
     quake
    0.05
     Bett
    0.05
    Activations Density 0.010%

    No Known Activations