© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16924
    Prev
    Next
    INDEX
    Explanations

    terms related to historical or architectural details

    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
    浩
    -0.07
    gate
    -0.07
     fleets
    -0.06
     Warp
    -0.06
    ISOString
    -0.06
     vs
    -0.06
    884
    -0.06
     diagonal
    -0.06
     SWAT
    -0.05
     crossover
    -0.05
    POSITIVE LOGITS
     Vz
    0.07
    ugo
    0.07
    ocy
    0.07
    浪
    0.07
    swire
    0.07
    .Timeout
    0.07
    icum
    0.07
    λÏį
    0.07
     Romeo
    0.06
     tiá»ģn
    0.06
    Activations Density 0.004%

    No Known Activations