© 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. 86698
    Prev
    Next
    INDEX
    Explanations

    references to artistic expression and identity

    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
    ynn
    -0.06
    -League
    -0.06
     Handy
    -0.06
     any
    -0.06
    ÙĮ
    -0.06
    nou
    -0.06
    enco
    -0.06
     Mad
    -0.05
     âĢķ
    -0.05
    ling
    -0.05
    POSITIVE LOGITS
     etc
    0.18
    etc
    0.17
     blah
    0.11
    /etc
    0.11
     ÑĤоÑīо
    0.11
     bla
    0.10
     ëĵ±ìĿĦ
    0.09
    çŃī
    0.09
    blah
    0.09
     forth
    0.09
    Activations Density 0.078%

    No Known Activations