© 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. 72741
    Prev
    Next
    INDEX
    Explanations

    references to handmade jewelry and metal types used in crafting

    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
    cano
    -0.07
     Metallic
    -0.07
    oni
    -0.06
     Bilg
    -0.06
    amil
    -0.06
    ForMember
    -0.06
    ublic
    -0.06
    oller
    -0.06
    asd
    -0.06
    ecko
    -0.06
    POSITIVE LOGITS
     Crystal
    0.08
     ruby
    0.08
    Crystal
    0.07
     crystal
    0.07
     Ruby
    0.07
     crystals
    0.07
     gem
    0.06
     size
    0.06
     mount
    0.06
     Mount
    0.06
    Activations Density 0.008%

    No Known Activations