© 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. 94765
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and related code structures

    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
    êt
    -0.07
    ething
    -0.07
    eless
    -0.07
    iaux
    -0.07
    alsa
    -0.07
    лÑİÑĩа
    -0.07
    enza
    -0.07
    лек
    -0.07
    ноÑģÑı
    -0.06
    eyh
    -0.06
    POSITIVE LOGITS
    -speaking
    0.08
    -native
    0.07
    .lang
    0.07
    -language
    0.07
    /java
    0.07
    -based
    0.07
    /.
    0.07
    /python
    0.06
    ian
    0.06
    itan
    0.06
    Activations Density 0.018%

    No Known Activations