© 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. 9-LLAMASCOPE-RES-131K
    11. 96998
    Prev
    Next
    INDEX
    Explanations

    instances of formal educational or community projects

    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
    rama
    -0.07
    kuk
    -0.07
     Bilim
    -0.06
    åįĴ
    -0.06
    inding
    -0.06
    loo
    -0.06
    dej
    -0.06
    ework
    -0.06
    äºĭåĭĻ
    -0.06
    rollers
    -0.06
    POSITIVE LOGITS
    odb
    0.07
    ahi
    0.06
     prise
    0.06
    blank
    0.06
    -shadow
    0.06
     srp
    0.06
     Carm
    0.06
    ÏģοÏħ
    0.06
    íĨ
    0.05
    oste
    0.05
    Activations Density 0.001%

    No Known Activations