© 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. 15-LLAMASCOPE-RES-131K
    11. 350
    Prev
    Next
    INDEX
    Explanations

    information related to dental qualifications and training

    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
    anes
    -0.06
    ale
    -0.06
     recourse
    -0.06
    hart
    -0.06
    brook
    -0.06
     Kamp
    -0.06
     carpets
    -0.05
     p
    -0.05
    atchet
    -0.05
     cons
    -0.05
    POSITIVE LOGITS
    ENCIL
    0.08
    UiThread
    0.07
     düz
    0.07
    _armor
    0.07
    uchen
    0.07
    .gg
    0.07
    _Destroy
    0.07
    าà¸
    0.07
    serter
    0.07
    erdem
    0.07
    Activations Density 0.005%

    No Known Activations