© 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. 17-LLAMASCOPE-RES-131K
    11. 118136
    Prev
    Next
    INDEX
    Explanations

    references to youth and their circumstances

    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
     itself
    -0.07
    verted
    -0.06
    太éĥİ
    -0.06
     Mundo
    -0.06
    endas
    -0.06
    /popper
    -0.06
    dsa
    -0.06
    andre
    -0.06
    undred
    -0.06
     hypers
    -0.06
    POSITIVE LOGITS
     whom
    0.07
    .pa
    0.07
     who
    0.07
     predic
    0.06
    IGNED
    0.06
    stdClass
    0.06
     quand
    0.06
     Lotus
    0.06
    utoff
    0.06
    icare
    0.06
    Activations Density 0.054%

    No Known Activations