© 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. 117631
    Prev
    Next
    INDEX
    Explanations

    specific time durations and measurements

    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
    .Validate
    -0.06
    OKEN
    -0.06
    tae
    -0.06
    ERA
    -0.06
     Sad
    -0.06
    one
    -0.06
     Esta
    -0.06
     Arm
    -0.06
    sonian
    -0.06
    //-
    -0.06
    POSITIVE LOGITS
     ë³´ë©´
    0.07
    Reached
    0.07
    acos
    0.06
     Reached
    0.06
    Point
    0.06
    quo
    0.06
    éłĥ
    0.06
    ago
    0.06
    athom
    0.06
    958
    0.06
    Activations Density 0.025%

    No Known Activations