© 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. 59134
    Prev
    Next
    INDEX
    Explanations

    the use of apostrophes in text, indicating possession or contractions

    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
    amment
    -0.08
    keit
    -0.08
    ntl
    -0.08
    dra
    -0.07
     Verfügung
    -0.07
    reiben
    -0.07
    luž
    -0.07
    iem
    -0.07
    ómo
    -0.06
    entiful
    -0.06
    POSITIVE LOGITS
    ris
    0.07
    295
    0.07
    407
    0.06
     robust
    0.06
    212
    0.06
    325
    0.06
    ola
    0.06
    æľŁ
    0.06
    PN
    0.05
    itter
    0.05
    Activations Density 0.000%

    No Known Activations