© 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. 106280
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks in the context of applications or downloads

    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
    reat
    -0.07
     â
    -0.07
    apo
    -0.06
    swire
    -0.06
    302
    -0.06
    231
    -0.06
    â
    -0.05
    豪
    -0.05
    021
    -0.05
    omic
    -0.05
    POSITIVE LOGITS
    лади
    0.08
    /tos
    0.08
    CSR
    0.07
    oader
    0.07
    йом
    0.07
    egrator
    0.07
     FAG
    0.07
    ãĥĨãĥ«
    0.07
    VERR
    0.07
    _Api
    0.07
    Activations Density 0.000%

    No Known Activations