© 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. 30754
    Prev
    Next
    INDEX
    Explanations

    concepts related to position, organization, and classification within a system

    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
    alytics
    -0.07
     adel
    -0.06
    enson
    -0.06
    vier
    -0.06
    izable
    -0.06
    annis
    -0.06
    .datab
    -0.06
    ải
    -0.06
    ym
    -0.06
    .RichTextBox
    -0.06
    POSITIVE LOGITS
     dint
    0.08
    º
    0.07
    incare
    0.06
    edn
    0.06
    ึà¸ģ
    0.06
    reso
    0.06
     majors
    0.06
    omatic
    0.06
    ynamo
    0.06
    à¸Ĥà¸Ńà¸ĩ
    0.06
    Activations Density 0.038%

    No Known Activations