© 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. 117494
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions or numerical data

    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
     tas
    -0.08
    ùa
    -0.08
     UIStoryboard
    -0.07
     Dillon
    -0.07
    tae
    -0.07
     اش
    -0.07
    isas
    -0.07
    owan
    -0.07
    rowned
    -0.07
    ılıç
    -0.07
    POSITIVE LOGITS
     hundreds
    0.08
     thousands
    0.08
    odom
    0.07
     hundred
    0.06
     dozens
    0.06
    Hundreds
    0.06
     Hundreds
    0.06
     Thousands
    0.06
    400
    0.06
     dozen
    0.06
    Activations Density 0.053%

    No Known Activations