© 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. 61497
    Prev
    Next
    INDEX
    Explanations

    high-level numerical data

    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
    kbd
    -0.07
    lid
    -0.07
    ebp
    -0.07
    icerca
    -0.07
     addCriterion
    -0.07
    ид
    -0.07
    olics
    -0.07
    моÑĢ
    -0.06
    /Dk
    -0.06
    -BEGIN
    -0.06
    POSITIVE LOGITS
    agit
    0.07
     carrying
    0.06
    oser
    0.06
     Gene
    0.06
     mission
    0.05
     businesses
    0.05
     Pad
    0.05
    greg
    0.05
     lag
    0.05
     Greg
    0.05
    Activations Density 0.000%

    No Known Activations