© 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. 15481
    Prev
    Next
    INDEX
    Explanations

    questions and identifiers related to specific professions or expertise

    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
    BarButton
    -0.06
     newArr
    -0.06
    ¦
    -0.05
    oup
    -0.05
    imest
    -0.05
    omi
    -0.05
    ItemImage
    -0.05
    owards
    -0.05
    IRST
    -0.05
    lef
    -0.05
    POSITIVE LOGITS
     below
    0.23
     Below
    0.22
    Below
    0.21
    below
    0.19
    以ä¸ĭ
    0.18
     BELOW
    0.16
    å¦Ĥä¸ĭ
    0.14
     following
    0.14
    ä¸ĭ
    0.13
     ìķĦëŀĺ
    0.13
    Activations Density 0.223%

    No Known Activations