© 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. 98416
    Prev
    Next
    INDEX
    Explanations

    references to programming or software components

    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
    olut
    -0.06
    eding
    -0.06
    ising
    -0.06
    inc
    -0.06
    iger
    -0.06
    issing
    -0.06
     inc
    -0.06
     Inc
    -0.06
    strup
    -0.06
    ropolis
    -0.06
    POSITIVE LOGITS
    hu
    0.07
    .getSeconds
    0.07
    ebek
    0.07
     Göz
    0.07
    -LAST
    0.07
    äºĪç´Ħ
    0.07
    iá»ĥu
    0.07
    lights
    0.07
    .Clone
    0.07
    LAY
    0.07
    Activations Density 0.065%

    No Known Activations