© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    references to themes of equality and diversity

    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
    ãģ¾ãģļ
    -0.09
     either
    -0.08
     firstly
    -0.08
     både
    -0.07
    ardi
    -0.07
     however
    -0.07
     EITHER
    -0.07
     allerdings
    -0.07
    	and
    -0.07
     však
    -0.07
    POSITIVE LOGITS
    /or
    0.19
    rogen
    0.12
    quot
    0.11
    /OR
    0.11
     consequ
    0.10
     subsequent
    0.10
     alike
    0.10
     therefore
    0.10
     subsequently
    0.09
     consequently
    0.09
    Activations Density 0.204%

    No Known Activations