© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3123
    Prev
    Next
    INDEX
    Explanations

    references to programming test cases and errors

    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
    ile
    -0.07
    rawn
    -0.06
    abric
    -0.06
    alg
    -0.06
    /ros
    -0.06
     ilç
    -0.06
    abar
    -0.06
    blem
    -0.05
    bris
    -0.05
    cade
    -0.05
    POSITIVE LOGITS
    overe
    0.08
    enberg
    0.07
    .did
    0.07
    oldt
    0.07
    opal
    0.07
    Occurred
    0.07
    BufferData
    0.06
    리ìĸ´
    0.06
    eneg
    0.06
    uito
    0.06
    Activations Density 0.000%

    No Known Activations