© 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. 70824
    Prev
    Next
    INDEX
    Explanations

    syntactical structures associated with exception 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
    ire
    -0.07
     nar
    -0.06
     hill
    -0.06
    ing
    -0.06
     gl
    -0.06
     Rel
    -0.06
    6
    -0.06
     g
    -0.05
    657
    -0.05
    sm
    -0.05
    POSITIVE LOGITS
    igli
    0.09
    AGIC
    0.08
    hait
    0.08
    xies
    0.08
    ilden
    0.07
    LOAT
    0.07
    AFX
    0.07
     Giul
    0.07
    odyn
    0.07
    JOR
    0.07
    Activations Density 0.008%

    No Known Activations