© 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. 86829
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and error handling constructs

    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
    omik
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
    /tiny
    -0.07
    ertino
    -0.06
    exus
    -0.06
     пода
    -0.06
    lest
    -0.06
    venience
    -0.06
    æ´¾
    -0.06
    ç«ĭãģ¦
    -0.06
    POSITIVE LOGITS
     &(
    0.07
    ICS
    0.07
     ages
    0.06
    ìĪĻ
    0.06
    ages
    0.06
     Exc
    0.06
    ain
    0.06
     exc
    0.06
    ings
    0.06
    obre
    0.06
    Activations Density 0.043%

    No Known Activations