© 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. 108546
    Prev
    Next
    INDEX
    Explanations

    expressions related to establishing or setting up projects or activities

    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
    dden
    -0.08
    dera
    -0.08
    uet
    -0.07
    quil
    -0.07
    odge
    -0.07
    å¢
    -0.07
    رÛĮÙĩ
    -0.07
    adle
    -0.07
    umbo
    -0.07
    JOR
    -0.06
    POSITIVE LOGITS
    tle
    0.14
     aside
    0.12
     forth
    0.11
     sail
    0.10
    elah
    0.09
    uptools
    0.09
    =set
    0.09
     Aside
    0.09
     Sail
    0.08
     up
    0.08
    Activations Density 0.022%

    No Known Activations