© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125178
    Prev
    Next
    INDEX
    Explanations

    occurrences of numeric values or code elements related to programming

    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
    -quarters
    -0.12
    /or
    -0.10
    ness
    -0.09
    zeit
    -0.08
    पत
    -0.08
    ing
    -0.08
    dür
    -0.08
    ship
    -0.08
    most
    -0.07
    ÚĨÙĩ
    -0.07
    POSITIVE LOGITS
    ãģ¾ãģŁ
    0.09
    elli
    0.08
     latter
    0.07
     importantly
    0.07
     ########.
    0.07
     ³³ ³³ ³³ ³³
    0.07
    ³³³³³³³³³
    0.07
    ates
    0.07
    wil
    0.07
    SSION
    0.07
    Activations Density 0.068%

    No Known Activations