© 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. 104157
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and medical confirmation 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
    ghan
    -0.07
     Wein
    -0.07
    ùi
    -0.07
    upert
    -0.07
    िशत
    -0.07
    inus
    -0.06
    asca
    -0.06
    illon
    -0.06
    asl
    -0.06
    asks
    -0.06
    POSITIVE LOGITS
    .atom
    0.06
    ).__
    0.06
     suspected
    0.06
    ecture
    0.06
    784
    0.06
     ANY
    0.05
    OUNT
    0.05
     Affero
    0.05
    olla
    0.05
    .wik
    0.05
    Activations Density 0.010%

    No Known Activations