© 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. 56421
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the inclusion or addition of features and elements

    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
    aeda
    -0.07
    CodeGen
    -0.07
    å¶
    -0.07
    Ã¶ÄŁ
    -0.07
    celik
    -0.07
    ODEV
    -0.07
    uard
    -0.07
    !..
    -0.07
    cott
    -0.07
    odge
    -0.07
    POSITIVE LOGITS
     includes
    0.10
     include
    0.10
     features
    0.09
     contains
    0.08
     feature
    0.08
    æľīä¸Ģ
    0.08
    include
    0.08
    features
    0.07
     Includes
    0.07
    includes
    0.07
    Activations Density 0.024%

    No Known Activations