© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    phrases related to making mistakes or poor choices

    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
    rung
    -0.07
    ypi
    -0.06
    é«ĺ度
    -0.06
     justification
    -0.06
    alm
    -0.06
     θÎŃ
    -0.06
    venta
    -0.06
    eller
    -0.06
    èį
    -0.06
    óg
    -0.06
    POSITIVE LOGITS
     wrong
    0.26
     correct
    0.23
    wrong
    0.21
     Wrong
    0.19
    Wrong
    0.19
    æŃ£ç¡®
    0.19
    correct
    0.18
     WRONG
    0.18
     incorrect
    0.17
     correctly
    0.17
    Activations Density 0.086%

    No Known Activations