© 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. 126715
    Prev
    Next
    INDEX
    Explanations

    elements related to programming logic and functionality, particularly within code snippets

    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
    iferay
    -0.07
    .getStyle
    -0.07
    обов
    -0.07
    .gwt
    -0.06
    chemas
    -0.06
     ìŀĪìĹĪ
    -0.06
    Ģ
    -0.06
    imuth
    -0.06
    jal
    -0.06
    å¸ĸ
    -0.06
    POSITIVE LOGITS
     ØŁ
    0.07
    erti
    0.07
    ï¿
    0.06
    aran
    0.06
    laz
    0.06
     Uncategorized
    0.06
    zar
    0.06
    ipple
    0.06
    won
    0.06
    iyon
    0.06
    Activations Density 0.087%

    No Known Activations