© 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. 75991
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to engineering and scientific research

    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
    åĬ¨çĶŁæĪIJ
    -0.06
     flows
    -0.06
     satire
    -0.06
     buffers
    -0.06
    ê³
    -0.06
     Sabbath
    -0.06
     Scr
    -0.06
    tid
    -0.05
     Gener
    -0.05
    r
    -0.05
    POSITIVE LOGITS
    oho
    0.08
    daq
    0.08
    FFFFFFFF
    0.07
    crement
    0.07
    LineNumber
    0.07
    Began
    0.07
    DAQ
    0.07
    SPAN
    0.07
    raison
    0.07
    ýt
    0.07
    Activations Density 0.004%

    No Known Activations