© 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. 89016
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence boundaries

    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
    Hopefully
    -0.07
     hopefully
    -0.07
     tomorrow
    -0.07
    eldom
    -0.07
     tonight
    -0.07
     Hopefully
    -0.06
    ras
    -0.06
    ILT
    -0.06
    chein
    -0.06
     today
    -0.06
    POSITIVE LOGITS
     myself
    0.08
    then
    0.08
     THEN
    0.07
     tane
    0.07
     basically
    0.07
    Ùħدة
    0.07
    illet
    0.07
    acÃŃ
    0.07
     then
    0.07
    after
    0.07
    Activations Density 0.035%

    No Known Activations