© 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 EvalsExportsinterp-engineNEWAPI 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. 81036
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "ly" and proper nouns

    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
    okt
    -0.07
    izon
    -0.07
    inem
    -0.06
    ivent
    -0.06
    acey
    -0.06
    ätt
    -0.06
    æł¼
    -0.06
    ounding
    -0.06
    immel
    -0.06
    adio
    -0.06
    POSITIVE LOGITS
    nn
    0.10
    eda
    0.08
    ea
    0.08
    eos
    0.07
    eo
    0.07
    ease
    0.07
    eder
    0.06
    eve
    0.06
    ìĦľëĬĶ
    0.06
    eing
    0.06
    Activations Density 0.016%

    No Known Activations