© 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. 15-LLAMASCOPE-RES-131K
    11. 103224
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and component 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
    iew
    -0.08
    iele
    -0.08
    islav
    -0.08
    agas
    -0.07
     actionTypes
    -0.07
    lav
    -0.07
    ãĥĥãĥī
    -0.07
    egas
    -0.07
    oplevel
    -0.07
    ResponseStatus
    -0.07
    POSITIVE LOGITS
    ÙĨس
    0.06
     Sak
    0.06
    ooks
    0.06
    789
    0.06
     Lew
    0.05
     Sof
    0.05
    pedia
    0.05
     business
    0.05
     Geh
    0.05
     ex
    0.05
    Activations Density 0.008%

    No Known Activations