© 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. 88788
    Prev
    Next
    INDEX
    Explanations

    numerical data and time-related references

    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
    2
    -0.07
    3
    -0.06
    icari
    -0.06
     Mey
    -0.06
    ictionary
    -0.06
    semi
    -0.06
    indr
    -0.05
    22
    -0.05
    feld
    -0.05
    erson
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.10
    ToOne
    0.08
    .ONE
    0.08
     findOne
    0.08
     ÄijÆ¡n
    0.07
    UNIT
    0.07
     ONE
    0.07
    åįķä½į
    0.07
    uner
    0.07
    illet
    0.07
    Activations Density 0.056%

    No Known Activations