© 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. 5581
    Prev
    Next
    INDEX
    Explanations

    words related to exceptions and error handling in programming

    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
    oki
    -0.08
    .scalablytyped
    -0.07
    eron
    -0.07
    ommen
    -0.07
    çĬ¬
    -0.07
    uke
    -0.07
    ilde
    -0.07
    omit
    -0.07
    rai
    -0.07
    vale
    -0.07
    POSITIVE LOGITS
    avr
    0.06
     Knox
    0.06
    218
    0.06
    ucz
    0.06
     Shannon
    0.06
     Transitional
    0.05
     fal
    0.05
     Shel
    0.05
     Denis
    0.05
     Clo
    0.05
    Activations Density 0.000%

    No Known Activations