© 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 EvalsExportsinterp-engineNEWAPI 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. 120153
    Prev
    Next
    INDEX
    Explanations

    references to computational technology and its advancements

    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
    anh
    -0.07
     Stations
    -0.07
    hang
    -0.07
     station
    -0.07
    lemn
    -0.07
    ertest
    -0.07
    wor
    -0.06
    ãĥĨãĥ«
    -0.06
    ENU
    -0.06
    æļ®
    -0.06
    POSITIVE LOGITS
     Moore
    0.08
    DRAM
    0.07
    ilip
    0.07
     Alone
    0.07
    [assembly
    0.07
    æij©
    0.06
    lef
    0.06
     åĬ
    0.06
    aliz
    0.06
    å¥Ī
    0.06
    Activations Density 0.012%

    No Known Activations