© 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. 92483
    Prev
    Next
    INDEX
    Explanations

    references to programming objects and data structures

    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
    ustin
    -0.07
    ffi
    -0.06
    ifton
    -0.06
    INCLUDED
    -0.06
     Pes
    -0.06
    μη
    -0.06
    isco
    -0.06
    úi
    -0.06
    oci
    -0.06
    ause
    -0.06
    POSITIVE LOGITS
    mah
    0.08
     helicopt
    0.07
    éĺħ读次æķ°
    0.07
    sWith
    0.07
    arith
    0.07
     Westbrook
    0.07
     æģ
    0.06
     chó
    0.06
    ãĥĩãĤ£ãĤ¢
    0.06
    سÙĪب
    0.06
    Activations Density 0.007%

    No Known Activations