© 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. 17-LLAMASCOPE-RES-131K
    11. 76624
    Prev
    Next
    INDEX
    Explanations

    JavaScript document manipulation commands

    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
    cura
    -0.07
    ừng
    -0.07
    ieux
    -0.07
     Brill
    -0.07
    illow
    -0.07
    orners
    -0.07
    uzu
    -0.06
     dostan
    -0.06
    ói
    -0.06
    printStats
    -0.06
    POSITIVE LOGITS
     Ober
    0.06
    abyrin
    0.06
    onas
    0.06
     Nass
    0.06
     bog
    0.06
    tap
    0.05
    :Add
    0.05
     Banner
    0.05
    .Add
    0.05
     Uncomment
    0.05
    Activations Density 0.006%

    No Known Activations