© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3632
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quality or classification of a product or service

    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
    ornings
    -0.06
     paddle
    -0.06
     correspond
    -0.06
    endant
    -0.06
    516
    -0.06
    567
    -0.06
     Till
    -0.06
    489
    -0.06
     stakes
    -0.06
    bei
    -0.05
    POSITIVE LOGITS
     sheer
    0.08
    iesen
    0.07
    sole
    0.07
    must
    0.07
    isser
    0.07
    dream
    0.07
    atra
    0.07
     must
    0.07
     dream
    0.07
    kill
    0.06
    Activations Density 0.045%

    No Known Activations