© 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. 17-LLAMASCOPE-RES-131K
    11. 29994
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transactions or exchanges

    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
    alta
    -0.07
    ufe
    -0.06
    åī£
    -0.06
    ippi
    -0.06
     grátis
    -0.06
    481
    -0.06
    solete
    -0.06
    ayi
    -0.06
    ift
    -0.06
    .bc
    -0.06
    POSITIVE LOGITS
     someone
    0.08
    someone
    0.07
     somebody
    0.07
     others
    0.07
    usz
    0.07
    another
    0.06
     another
    0.06
    _CLI
    0.06
    etu
    0.06
     hamburger
    0.06
    Activations Density 0.013%

    No Known Activations