© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 83009
    Prev
    Next
    INDEX
    Explanations

    mentions of lasers 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
    sell
    -0.08
    ações
    -0.08
    sys
    -0.07
    sk
    -0.07
    ents
    -0.07
    elist
    -0.07
    ea
    -0.07
    iard
    -0.06
    ação
    -0.06
    utions
    -0.06
    POSITIVE LOGITS
    ized
    0.08
    Ĥæķ°
    0.08
    onde
    0.07
    ÄįÃŃ
    0.07
    Ïģιά
    0.07
    arine
    0.07
    antha
    0.07
    езда
    0.06
     cutting
    0.06
    asio
    0.06
    Activations Density 0.004%

    No Known Activations