© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3856
    Prev
    Next
    INDEX
    Explanations

    references to data or statistics related to time periods

    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
    rost
    -0.07
    aths
    -0.07
    ewe
    -0.07
    ovel
    -0.07
    opping
    -0.07
    UNET
    -0.07
    #.
    -0.07
    erp
    -0.07
    liÄŁinde
    -0.07
    eric
    -0.06
    POSITIVE LOGITS
    198
    0.09
    199
    0.09
    197
    0.08
    195
    0.08
     Jan
    0.08
    194
    0.08
    196
    0.08
     between
    0.07
     January
    0.07
    200
    0.07
    Activations Density 0.072%

    No Known Activations