© 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. 74417
    Prev
    Next
    INDEX
    Explanations

    numeric specifications and measurements related to materials and machinery

    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
    estre
    -0.07
    uja
    -0.06
    bang
    -0.06
    icha
    -0.06
    assin
    -0.06
    ILog
    -0.06
     Slut
    -0.06
     ep
    -0.06
     Bulk
    -0.06
     Childhood
    -0.06
    POSITIVE LOGITS
     Bis
    0.07
    inox
    0.06
    aday
    0.06
    ¼
    0.06
    PN
    0.06
    ächst
    0.06
    shm
    0.06
    regor
    0.06
    weigh
    0.06
    opyright
    0.06
    Activations Density 0.013%

    No Known Activations