© 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. 55084
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to reactions and activities in materials

    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
    okable
    -0.08
    orc
    -0.08
    ockey
    -0.07
    entanyl
    -0.07
    UGIN
    -0.07
     éº
    -0.07
    iquer
    -0.07
    pak
    -0.07
    braco
    -0.07
    еÑĢап
    -0.07
    POSITIVE LOGITS
     solar
    0.13
     Solar
    0.12
    Solar
    0.11
     sunlight
    0.09
     sun
    0.09
     photo
    0.08
     Sun
    0.08
    sun
    0.07
     sunscreen
    0.07
    .sun
    0.07
    Activations Density 0.014%

    No Known Activations