© 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. 89381
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" in various contexts

    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
    avra
    -0.07
    wart
    -0.07
    çķĮ
    -0.07
     Genome
    -0.06
    pread
    -0.06
    ripper
    -0.06
    .infinity
    -0.06
    aleb
    -0.06
    efault
    -0.06
    åŀĭ
    -0.06
    POSITIVE LOGITS
     basis
    0.08
     behalf
    0.07
     grounds
    0.07
     βά
    0.06
    illard
    0.06
     abs
    0.06
     occasion
    0.06
    ãĥ©ãĥ¼
    0.06
     pri
    0.06
    Ñįн
    0.05
    Activations Density 0.051%

    No Known Activations