© 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 EvalsExportsinterp-engineNEWAPI 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. 17420
    Prev
    Next
    INDEX
    Explanations

    terms related to internet and Wi-Fi access in accommodations

    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
    lector
    -0.07
    presso
    -0.06
    avid
    -0.06
    lobs
    -0.06
    ÌĤ
    -0.06
    obo
    -0.06
    phants
    -0.06
    ssf
    -0.06
     Ez
    -0.06
    enerator
    -0.06
    POSITIVE LOGITS
    orp
    0.08
    uta
    0.07
    internet
    0.07
    _BS
    0.06
    ocop
    0.06
     Becker
    0.06
     سخ
    0.06
    emd
    0.06
     throughout
    0.06
    subpackage
    0.06
    Activations Density 0.002%

    No Known Activations