© 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. 126583
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to material properties and semiconductor technology

    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
    asis
    -0.06
    [:]
    -0.06
    PostExecute
    -0.06
     Freed
    -0.06
     Portug
    -0.06
    lok
    -0.06
     criteria
    -0.06
    Ñı
    -0.06
     Geld
    -0.05
     Folding
    -0.05
    POSITIVE LOGITS
     layer
    0.11
     layers
    0.11
     Layers
    0.10
    layers
    0.10
    層
    0.10
    å±Ĥ
    0.09
    Layers
    0.09
     addCriterion
    0.09
    layer
    0.09
    _layers
    0.09
    Activations Density 0.014%

    No Known Activations