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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29728
    Prev
    Next
    INDEX
    Explanations

    various programming elements and structures, particularly in code snippets and configuration files

    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
    Æ°Æ¡
    -0.07
    te
    -0.06
    lom
    -0.06
    بÛĮÙĨÛĮ
    -0.06
     Airport
    -0.06
    uster
    -0.06
    aged
    -0.06
    ett
    -0.06
    zzo
    -0.06
    .rc
    -0.06
    POSITIVE LOGITS
    addtogroup
    0.08
    defgroup
    0.07
    以ä¸Ĭ
    0.07
    -grand
    0.07
    ignKey
    0.07
    ãĥ³ãĥĦ
    0.06
    _wf
    0.06
    oldem
    0.06
    ανά
    0.06
     TMPro
    0.06
    Activations Density 0.016%

    No Known Activations