© 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. 4707
    Prev
    Next
    INDEX
    Explanations

    syntax-related symbols and punctuation in code samples

    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
    ascus
    -0.08
    ŀ
    -0.07
    mah
    -0.07
    essel
    -0.07
    byn
    -0.07
    èī²çļĦ
    -0.07
    leck
    -0.07
    å¾ĵ
    -0.07
    ails
    -0.07
    вод
    -0.07
    POSITIVE LOGITS
    reb
    0.06
    TEL
    0.06
     Clem
    0.06
     inherited
    0.06
     Ridley
    0.06
    710
    0.06
     Wal
    0.05
    ená
    0.05
     com
    0.05
     Isaac
    0.05
    Activations Density 0.002%

    No Known Activations