© 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. 124053
    Prev
    Next
    INDEX
    Explanations

    phrases indicating technical problems or troubleshooting steps

    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
    s
    -0.08
    aroo
    -0.07
    веÑĢд
    -0.07
    Ấ
    -0.07
     Armour
    -0.07
    rade
    -0.07
     Icons
    -0.06
    "+"
    -0.06
     SaÄŁ
    -0.06
    uplic
    -0.06
    POSITIVE LOGITS
    AXB
    0.07
     بÙĪابة
    0.06
    ItemCount
    0.06
    allen
    0.06
    etheless
    0.06
    whel
    0.06
    617
    0.06
     alike
    0.06
    tright
    0.05
     scales
    0.05
    Activations Density 0.019%

    No Known Activations