© 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. 75082
    Prev
    Next
    INDEX
    Explanations

    words related to understanding and realization

    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
    .Dependency
    -0.07
     faiz
    -0.07
     inode
    -0.07
    /;↵
    -0.07
     každé
    -0.07
    à¥ĭà¤ļ
    -0.07
     jejÃŃm
    -0.07
    еÑĦ
    -0.06
    ĮĢ
    -0.06
    .big
    -0.06
    POSITIVE LOGITS
    je
    0.06
    ,
    0.06
    hm
    0.06
    aines
    0.06
    usercontent
    0.06
     res
    0.06
    jer
    0.05
     contact
    0.05
    :
    0.05
    ns
    0.05
    Activations Density 0.000%

    No Known Activations