© 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. 86669
    Prev
    Next
    INDEX
    Explanations

    references to notable firsts, especially regarding gender and race in various fields

    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
    isin
    -0.09
    iskey
    -0.07
    inx
    -0.07
    issen
    -0.07
    aines
    -0.06
    ãģªãģĹ
    -0.06
    ouns
    -0.06
    ï¸ı
    -0.06
    /apps
    -0.06
    ADATA
    -0.06
    POSITIVE LOGITS
     recorded
    0.07
     inkl
    0.07
    -ever
    0.07
     Valentine
    0.07
     ever
    0.06
    orsche
    0.06
     @{
    0.06
    /original
    0.06
     láºŃp
    0.06
     Recorded
    0.06
    Activations Density 0.026%

    No Known Activations