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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126623
    Prev
    Next
    INDEX
    Explanations

    references to diverse entities and roles within narratives or contexts

    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
     å¹
    -0.07
    187
    -0.06
    razy
    -0.06
    904
    -0.06
    erna
    -0.06
    ignet
    -0.06
    outh
    -0.06
    573
    -0.06
     ä¸
    -0.06
    icros
    -0.06
    POSITIVE LOGITS
     whose
    0.11
     otherwise
    0.09
     already
    0.09
    whose
    0.07
     proven
    0.07
    nect
    0.07
     that
    0.07
     which
    0.07
     vá»ijn
    0.06
     Otherwise
    0.06
    Activations Density 0.024%

    No Known Activations