© 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. 60974
    Prev
    Next
    INDEX
    Explanations

    terms related to internet speed and data connectivity

    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
    EEP
    -0.07
    ÙĦØŃ
    -0.07
    irler
    -0.07
     даÑĤ
    -0.07
    ÏĦεÏħ
    -0.07
    compact
    -0.06
    ipi
    -0.06
    inline
    -0.06
     wearer
    -0.06
     preds
    -0.06
    POSITIVE LOGITS
     speeds
    0.11
    .speed
    0.10
    speed
    0.10
    peed
    0.09
     Speed
    0.09
    -speed
    0.09
     speed
    0.09
    Speed
    0.08
    .Speed
    0.08
    éĢŁåº¦
    0.07
    Activations Density 0.011%

    No Known Activations