© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 82804
    Prev
    Next
    INDEX
    Explanations

    formatting symbols and attributes in XML or HTML code

    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
    ellas
    -0.07
    OOM
    -0.07
    MSN
    -0.07
    æ¿
    -0.07
    akit
    -0.07
    ekim
    -0.07
    erland
    -0.06
    onder
    -0.06
    celik
    -0.06
    ARP
    -0.06
    POSITIVE LOGITS
     Bened
    0.07
     Ty
    0.07
     ty
    0.06
    aza
    0.06
    778
    0.06
    ugg
    0.06
    ework
    0.06
    fila
    0.06
     Zuk
    0.06
    agle
    0.06
    Activations Density 0.002%

    No Known Activations