© 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. 62787
    Prev
    Next
    INDEX
    Explanations

    content related to print media and publications

    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
    etz
    -0.07
    chner
    -0.06
     Eg
    -0.06
    çĶ°
    -0.06
     microscopic
    -0.06
     borderBottom
    -0.06
    PIO
    -0.06
    illard
    -0.06
    leys
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
     print
    0.07
    avana
    0.07
    (Print
    0.07
    liÄŁ
    0.06
    ourg
    0.06
    /print
    0.06
    หาย
    0.06
     Print
    0.06
    Material
    0.06
     ÙĥبÙĬر
    0.06
    Activations Density 0.006%

    No Known Activations