© 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. 5-LLAMASCOPE-RES-131K
    11. 125993
    Prev
    Next
    INDEX
    Explanations

    function declarations in code

    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
    амеÑĤ
    -0.07
    ÛĮÙĨÙĩ
    -0.07
    ToF
    -0.07
    ãĥ³ãĥIJãĥ¼
    -0.06
    sono
    -0.06
    XObject
    -0.06
    .metamodel
    -0.06
    .modules
    -0.06
    RLF
    -0.06
    EEP
    -0.06
    POSITIVE LOGITS
    ammen
    0.06
     kÃ¶ÅŁ
    0.06
    ëĤĺ
    0.06
    rias
    0.06
    Äı
    0.06
    596
    0.06
    æ²Ļ
    0.06
    лаг
    0.06
     Irving
    0.06
    aben
    0.06
    Activations Density 0.012%

    No Known Activations