© 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. 29166
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disclaimers or warranties

    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
    ibel
    -0.07
    imson
    -0.07
    IBUTE
    -0.07
    ILLISE
    -0.07
    omic
    -0.07
    æŀ
    -0.07
    repid
    -0.06
     "&#
    -0.06
    reck
    -0.06
    itech
    -0.06
    POSITIVE LOGITS
    _DIRS
    0.07
     Osw
    0.06
    ulfilled
    0.06
    gle
    0.06
     EITHER
    0.05
    IPP
    0.05
     Fel
    0.05
    ots
    0.05
     Dawson
    0.05
     Ñģебе
    0.05
    Activations Density 0.001%

    No Known Activations