© 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. 30189
    Prev
    Next
    INDEX
    Explanations

    expressions related to problem-solving and troubleshooting

    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
    434
    -0.07
    à¹Īà¸Ńม
    -0.07
     shopping
    -0.06
    ai
    -0.06
    /pi
    -0.06
     catalog
    -0.06
     spell
    -0.06
    iy
    -0.06
    ener
    -0.06
    rap
    -0.05
    POSITIVE LOGITS
    vanished
    0.08
    solution
    0.08
     posted
    0.07
    ģm
    0.07
    uitka
    0.07
     applicable
    0.07
    ëĿ½
    0.07
     solutions
    0.07
     posts
    0.07
    éģ©çĶ¨
    0.07
    Activations Density 0.008%

    No Known Activations