© 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. 126139
    Prev
    Next
    INDEX
    Explanations

    terms related to racing circuits and events

    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
    mare
    -0.06
    dney
    -0.06
     Budget
    -0.05
    man
    -0.05
    olie
    -0.05
    ä¹Ĺ
    -0.05
    327
    -0.05
    ude
    -0.05
     sı
    -0.05
    iyeti
    -0.05
    POSITIVE LOGITS
    lox
    0.08
    á»ĩu
    0.08
     sami
    0.08
    TokenType
    0.07
    ırı
    0.07
    iferay
    0.07
    è·¡
    0.07
    ildo
    0.07
    êu
    0.07
    ì´Ŀ
    0.07
    Activations Density 0.145%

    No Known Activations