© 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. 94536
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and strategic decision-making

    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
    ezi
    -0.07
    oret
    -0.07
    ãĥĥãĤ¯
    -0.07
    ÙĨب
    -0.07
    ojis
    -0.07
    erosis
    -0.07
    redo
    -0.07
    ISO
    -0.07
    reon
    -0.07
    IFO
    -0.06
    POSITIVE LOGITS
    marketing
    0.07
     mailing
    0.06
    .osgi
    0.06
    éĤ®
    0.06
    errat
    0.06
    ottage
    0.06
    gmail
    0.05
    αιν
    0.05
    á»ķ
    0.05
     CS
    0.05
    Activations Density 0.004%

    No Known Activations