© 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. 15-LLAMASCOPE-RES-131K
    11. 88703
    Prev
    Next
    INDEX
    Explanations

    geographical locations and associated details

    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
    iev
    -0.07
    inho
    -0.06
     compressed
    -0.06
     Yuan
    -0.05
     clocks
    -0.05
    dap
    -0.05
     Gut
    -0.05
     dec
    -0.05
    igon
    -0.05
    -l
    -0.05
    POSITIVE LOGITS
    esor
    0.07
    ÏĥÏĦαν
    0.07
    iser
    0.07
    عاÙĨ
    0.07
    ogue
    0.07
    606
    0.07
    URT
    0.06
    redential
    0.06
    abler
    0.06
    antro
    0.06
    Activations Density 0.008%

    No Known Activations