© 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. 125166
    Prev
    Next
    INDEX
    Explanations

    references to television channels and broadcasting details

    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
    اÙĬر
    -0.07
     prostitutas
    -0.07
    ProcessEvent
    -0.07
    anio
    -0.06
    atsu
    -0.06
    esub
    -0.06
     mainBundle
    -0.06
    alach
    -0.06
     submission
    -0.06
     sesso
    -0.06
    POSITIVE LOGITS
     Programming
    0.08
     programming
    0.08
    Programming
    0.07
    oco
    0.07
     Programmer
    0.06
    èģ
    0.06
    programming
    0.06
    443
    0.06
     content
    0.06
     licensee
    0.06
    Activations Density 0.001%

    No Known Activations