© 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. 56588
    Prev
    Next
    INDEX
    Explanations

    references to the inability to learn from past mistakes

    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
    ood
    -0.09
    oleon
    -0.07
    ledger
    -0.07
    ritos
    -0.07
    emade
    -0.07
    emailer
    -0.07
    ighter
    -0.07
    utdown
    -0.07
    EXTERN
    -0.07
    arget
    -0.07
    POSITIVE LOGITS
     understanding
    0.09
     comprehension
    0.09
     Wake
    0.09
     understand
    0.08
     lesson
    0.08
     Lesson
    0.08
     understood
    0.08
     comprehend
    0.07
     lessons
    0.07
     Understanding
    0.07
    Activations Density 0.052%

    No Known Activations