© 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. 30252
    Prev
    Next
    INDEX
    Explanations

    key objectives and outcomes of scientific research trials

    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
    irut
    -0.07
    enia
    -0.07
    enet
    -0.07
    iac
    -0.06
    aal
    -0.06
     rival
    -0.06
     lecture
    -0.06
    inclu
    -0.06
    kul
    -0.06
    enal
    -0.05
    POSITIVE LOGITS
     aims
    0.09
     conduc
    0.09
     objectives
    0.08
    ìĹ°êµ¬
    0.07
     objetivo
    0.07
     aim
    0.07
     nghiên
    0.07
     goals
    0.07
     TMPro
    0.07
     ÙĩدÙģ
    0.07
    Activations Density 0.023%

    No Known Activations