© 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. 88447
    Prev
    Next
    INDEX
    Explanations

    phrases related to the necessity or desire for escape or adventure

    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
    deaux
    -0.08
    anela
    -0.07
    _BINDING
    -0.06
    etCode
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    amar
    -0.06
    upy
    -0.06
     ele
    -0.06
    rand
    -0.06
     wah
    -0.06
    POSITIVE LOGITS
     therefore
    0.08
    Therefore
    0.07
    edm
    0.07
    ï¼ĮæīĢ以
    0.06
     Therefore
    0.06
     Walsh
    0.06
    -bodied
    0.06
     autoload
    0.06
    Ñıн
    0.06
     ÐŁÐ¾ÑįÑĤомÑĥ
    0.06
    Activations Density 0.009%

    No Known Activations