© 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. 60596
    Prev
    Next
    INDEX
    Explanations

    locations and settings described in the text

    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
     immediate
    -0.08
     Rosenstein
    -0.07
     Immediate
    -0.07
    IRR
    -0.07
    ambah
    -0.07
    unas
    -0.07
    icie
    -0.07
    živ
    -0.07
    irie
    -0.07
    494
    -0.07
    POSITIVE LOGITS
     many
    0.08
     most
    0.06
     unwanted
    0.06
     exactly
    0.06
    UGH
    0.06
    Å¡k
    0.06
     Ben
    0.06
    rou
    0.06
    _DX
    0.06
     countless
    0.06
    Activations Density 0.013%

    No Known Activations