© 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. 15959
    Prev
    Next
    INDEX
    Explanations

    concepts related to community and shared experiences

    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
    ãĤ©
    -0.07
    360
    -0.07
    اÙĤ
    -0.07
    772
    -0.07
    forme
    -0.07
    iets
    -0.06
    590
    -0.06
    اعÙĬ
    -0.06
    eel
    -0.06
    lopen
    -0.06
    POSITIVE LOGITS
     aside
    0.10
     puts
    0.09
     zusammen
    0.08
     into
    0.08
     emphasis
    0.08
    _into
    0.08
    aside
    0.07
     Aside
    0.07
     Into
    0.07
    zed
    0.07
    Activations Density 0.047%

    No Known Activations