© 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. 94826
    Prev
    Next
    INDEX
    Explanations

    variations of the term "UTF" relating to character encoding

    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
    loff
    -0.07
    erot
    -0.07
    Ñģлов
    -0.06
    lef
    -0.06
    деÑĢж
    -0.06
    lej
    -0.06
    rozen
    -0.06
    кин
    -0.06
    isor
    -0.06
    lemn
    -0.06
    POSITIVE LOGITS
    ighton
    0.06
    pac
    0.06
     Steel
    0.06
     inher
    0.06
    .GetBytes
    0.06
    .Sdk
    0.06
     Fighter
    0.06
    _TestCase
    0.06
     ucwords
    0.05
    olid
    0.05
    Activations Density 0.000%

    No Known Activations