© 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. 9-LLAMASCOPE-RES-131K
    11. 97085
    Prev
    Next
    INDEX
    Explanations

    references to email communication and management processes

    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
    PLL
    -0.07
    ictor
    -0.07
    ssid
    -0.07
    iste
    -0.06
    isti
    -0.06
    aucoup
    -0.06
     подв
    -0.06
    istes
    -0.06
    _ABI
    -0.06
    ¢åįķ
    -0.06
    POSITIVE LOGITS
    TargetException
    0.06
    itler
    0.06
    infer
    0.06
    adle
    0.06
     targets
    0.06
    onz
    0.06
     distrib
    0.06
    _deinit
    0.06
    onde
    0.06
     Distrib
    0.06
    Activations Density 0.030%

    No Known Activations