© 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. 79888
    Prev
    Next
    INDEX
    Explanations

    statistics related to job resignation rates across different states

    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
     hete
    -0.08
    Ãłng
    -0.07
    iores
    -0.07
    altura
    -0.07
    ButtonType
    -0.07
    	DECLARE
    -0.07
     èı²å¾ĭ宾
    -0.07
    agg
    -0.07
    ynet
    -0.07
    aned
    -0.07
    POSITIVE LOGITS
    cher
    0.07
     Fare
    0.06
     residents
    0.06
     pod
    0.06
     Stat
    0.06
     where
    0.06
     Hay
    0.06
     pair
    0.06
     value
    0.05
     Least
    0.05
    Activations Density 0.007%

    No Known Activations