© 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. 126935
    Prev
    Next
    INDEX
    Explanations

    environment variable settings related to Java and configuration parameters

    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
    	Copyright
    -0.08
     $('#'
    -0.07
    modele
    -0.07
     toItem
    -0.07
    ænd
    -0.07
     ìĪľê°Ħ
    -0.07
    áj
    -0.07
    SpaceItem
    -0.07
    baugh
    -0.07
    InitStruct
    -0.07
    POSITIVE LOGITS
     environment
    0.07
     environmental
    0.06
     n
    0.06
     rar
    0.06
     Vend
    0.06
     envi
    0.06
    cth
    0.06
    ugo
    0.06
     Synd
    0.06
     variable
    0.06
    Activations Density 0.050%

    No Known Activations