© 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. 87491
    Prev
    Next
    INDEX
    Explanations

    contractions and other informal forms of expression in a text

    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
    redi
    -0.07
    reh
    -0.06
    olib
    -0.06
    _cp
    -0.06
    ½æķ°
    -0.06
    ắc
    -0.05
     reg
    -0.05
    еи
    -0.05
    Vect
    -0.05
     kata
    -0.05
    POSITIVE LOGITS
    occ
    0.07
    utoff
    0.07
    ucz
    0.07
    ucus
    0.07
    anical
    0.07
     mRecyclerView
    0.07
    quina
    0.06
    ILI
    0.06
    oucher
    0.06
    makta
    0.06
    Activations Density 0.002%

    No Known Activations