© 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. 9-LLAMASCOPE-RES-131K
    11. 97613
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that end in "ed"

    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
    assen
    -0.07
    977
    -0.07
    OTES
    -0.07
    ासन
    -0.06
    Intent
    -0.06
    usz
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    avern
    -0.06
    bis
    -0.06
    elong
    -0.06
    POSITIVE LOGITS
    cxx
    0.06
    vanced
    0.06
    igham
    0.06
    ople
    0.06
    RunWith
    0.06
    acker
    0.06
    .manual
    0.06
     Baghd
    0.06
    aml
    0.05
     impression
    0.05
    Activations Density 0.000%

    No Known Activations