© 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. 55045
    Prev
    Next
    INDEX
    Explanations

    distinct identifiers or significance in names and titles related to literary and philosophical works

    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
    eton
    -0.08
    DAQ
    -0.07
    etty
    -0.07
    741
    -0.07
    alse
    -0.07
    ิà¸Ħ
    -0.07
    IODevice
    -0.07
    enze
    -0.07
    /misc
    -0.07
    edor
    -0.07
    POSITIVE LOGITS
     Balls
    0.07
    zilla
    0.06
    ovit
    0.06
     Loren
    0.06
    adb
    0.06
    .selenium
    0.06
     cre
    0.06
    ked
    0.05
    ables
    0.05
     automatic
    0.05
    Activations Density 0.014%

    No Known Activations