© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127312
    Prev
    Next
    INDEX
    Explanations

    structured data related to demographics and genres in a descriptive context

    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
     record
    -0.07
     Daly
    -0.06
     form
    -0.06
     live
    -0.06
    asta
    -0.06
    arpa
    -0.06
     tip
    -0.06
    zu
    -0.05
     land
    -0.05
    ollah
    -0.05
    POSITIVE LOGITS
    ukan
    0.08
    allon
    0.08
     fic
    0.07
    ÏĩεδÏĮν
    0.07
     Ñĩа
    0.07
    imson
    0.07
     DISCLAIMER
    0.07
    icer
    0.07
    --[[
    0.07
    oyer
    0.07
    Activations Density 0.024%

    No Known Activations