© 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 EvalsExportsinterp-engineNEWAPI 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. 27295
    Prev
    Next
    INDEX
    Explanations

    significant numerical values and associated terms

    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
    bor
    -0.07
    reet
    -0.07
    emouth
    -0.07
    ogne
    -0.07
    emm
    -0.07
     norge
    -0.06
    bian
    -0.06
    ELLOW
    -0.06
    UNCH
    -0.06
    /gtest
    -0.06
    POSITIVE LOGITS
     third
    0.17
     Third
    0.16
     第ä¸ī
    0.15
    third
    0.15
    第ä¸ī
    0.15
    Third
    0.15
    3
    0.15
     THIRD
    0.15
     Three
    0.14
     thirds
    0.14
    Activations Density 0.059%

    No Known Activations