© 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. 82960
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions and award selections

    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
    anka
    -0.08
    icc
    -0.07
    emonic
    -0.06
    combe
    -0.06
    /save
    -0.06
    Spacer
    -0.06
    holm
    -0.06
     Flint
    -0.06
    anian
    -0.06
     linkage
    -0.06
    POSITIVE LOGITS
    chosen
    0.08
     chosen
    0.07
     selected
    0.07
    selected
    0.07
    represent
    0.06
    _mr
    0.06
     nave
    0.06
     met
    0.06
    vet
    0.06
     aras
    0.06
    Activations Density 0.026%

    No Known Activations