© 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. 73503
    Prev
    Next
    INDEX
    Explanations

    references to time and chronological events

    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
    croft
    -0.08
    eton
    -0.08
    $MESS
    -0.07
    isas
    -0.07
    isque
    -0.07
    érica
    -0.07
    elease
    -0.07
    ulares
    -0.07
     íĬ¹íŀĪ
    -0.06
    mand
    -0.06
    POSITIVE LOGITS
    Ïĥκε
    0.06
     zwar
    0.06
    /dat
    0.06
     spr
    0.06
     late
    0.06
     end
    0.06
    aus
    0.06
    aled
    0.06
    0.05
    it
    0.05
    Activations Density 0.031%

    No Known Activations