© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    references to funding or financial support for projects or institutions

    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
    orgot
    -0.07
    orsch
    -0.07
    onomic
    -0.07
    625
    -0.06
    828
    -0.06
    EOS
    -0.06
    onom
    -0.06
    Berry
    -0.06
    stk
    -0.06
    uv
    -0.06
    POSITIVE LOGITS
    amental
    0.11
    ksiyon
    0.08
    amentals
    0.08
    sett
    0.07
    ymoon
    0.07
    urma
    0.07
    isseur
    0.07
    ness
    0.07
    ãģ¼
    0.07
    afone
    0.07
    Activations Density 0.005%

    No Known Activations