© 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. 126167
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant moments or changes in a situation

    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
     McKay
    -0.06
    ihn
    -0.06
    _EC
    -0.06
    nez
    -0.06
     Jenner
    -0.06
    ecer
    -0.06
    faker
    -0.05
    .YesNo
    -0.05
     Lamp
    -0.05
     nearest
    -0.05
    POSITIVE LOGITS
    retty
    0.08
     timing
    0.07
     Timing
    0.07
     times
    0.06
     opport
    0.06
    bÃŃ
    0.06
    uje
    0.06
    ÑĢиг
    0.06
    .Debugger
    0.06
     seedu
    0.06
    Activations Density 0.005%

    No Known Activations