© 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. 125753
    Prev
    Next
    INDEX
    Explanations

    various aspects of hospitality service and guest 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
    VERR
    -0.08
    ãĥĥãĤ°
    -0.08
    ISTRIBUT
    -0.07
    NSBundle
    -0.07
     miscellaneous
    -0.07
    istik
    -0.07
    unya
    -0.07
     quickest
    -0.07
    _SDK
    -0.07
    تÙĪاÙĨ
    -0.07
    POSITIVE LOGITS
     throughout
    0.10
     every
    0.09
     each
    0.07
     Throughout
    0.06
     unlike
    0.06
     twice
    0.06
     ensures
    0.06
    every
    0.06
     upon
    0.06
    ola
    0.06
    Activations Density 0.021%

    No Known Activations