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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14558
    Prev
    Next
    INDEX
    Explanations

    concepts related to communication and connection through the internet

    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
    strup
    -0.06
     Safe
    -0.06
     mentioned
    -0.06
    atri
    -0.06
     res
    -0.06
     telegram
    -0.06
    rix
    -0.06
     Rog
    -0.06
    ader
    -0.05
    coop
    -0.05
    POSITIVE LOGITS
     DÃŃky
    0.09
    çŀ¬
    0.08
     billig
    0.07
    å¨ĺ
    0.07
    baum
    0.07
     access
    0.07
     ydk
    0.07
     snadno
    0.07
    WithMany
    0.07
    اسÛĮ
    0.07
    Activations Density 0.044%

    No Known Activations