© 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. 9-LLAMASCOPE-RES-131K
    11. 98272
    Prev
    Next
    INDEX
    Explanations

    mathematical statements involving existence and conditions of sets and functions

    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
    DAQ
    -0.07
     prostitu
    -0.07
    bard
    -0.07
    jerne
    -0.07
    ebra
    -0.07
    illac
    -0.06
     dán
    -0.06
     OST
    -0.06
     Arena
    -0.06
    aus
    -0.06
    POSITIVE LOGITS
     Dip
    0.07
     McConnell
    0.06
    243
    0.06
    ê
    0.06
    okt
    0.06
    ãĥĥãĤ¯
    0.06
    ater
    0.05
    raki
    0.05
    akk
    0.05
    Äįet
    0.05
    Activations Density 0.169%

    No Known Activations