© 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. 39717
    Prev
    Next
    INDEX
    Explanations

    discussions about government transparency and openness

    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
    æ¿
    -0.07
    ãģ£ãģ¡
    -0.07
    urette
    -0.07
    åİŁå§ĭ
    -0.07
    æĸ°èģŀ
    -0.07
    éĻħ
    -0.07
     вида
    -0.07
    XA
    -0.07
    Îĸ
    -0.07
     AÅŁ
    -0.07
    POSITIVE LOGITS
     hypoth
    0.07
     platform
    0.07
    hol
    0.06
     immediately
    0.06
    ampion
    0.06
    uli
    0.06
    holm
    0.06
    omor
    0.06
     would
    0.06
    adele
    0.06
    Activations Density 0.031%

    No Known Activations