© 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. 9-LLAMASCOPE-RES-131K
    11. 97643
    Prev
    Next
    INDEX
    Explanations

    conversational greetings and expressions of concern

    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
    ceed
    -0.07
    ieux
    -0.07
    ddy
    -0.06
    illo
    -0.06
    omic
    -0.06
    pac
    -0.06
    men
    -0.06
    idal
    -0.06
    ãĤ¯ãĥĪ
    -0.06
    ôm
    -0.06
    POSITIVE LOGITS
    olib
    0.07
    Ÿ
    0.07
    usan
    0.06
     ulus
    0.06
    409
    0.06
    136
    0.06
    orthand
    0.06
    رÙĪØ´
    0.06
     cán
    0.06
    ì£Ħ
    0.06
    Activations Density 0.006%

    No Known Activations