Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56215
    Prev
    Next
    INDEX
    Explanations

    elements related to programming, particularly in the context of shaders and data types

    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
    celik
    -0.08
    herit
    -0.07
    ichni
    -0.07
    ç¿
    -0.07
    rint
    -0.06
    ebi
    -0.06
     NSK
    -0.06
    να
    -0.06
    erk
    -0.06
     ÙĨاØŃÛĮÙĩ
    -0.06
    POSITIVE LOGITS
     *
    0.07
    ắ
    0.07
    ¤
    0.06
    çĴ
    0.06
    ména
    0.06
    lus
    0.06
    IJ
    0.06
    *
    0.06
    .Companion
    0.06
    atrix
    0.06
    Activations Density 0.073%

    No Known Activations