© 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. 119215
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recently."

    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
    aret
    -0.07
    acus
    -0.07
    velt
    -0.07
    ÙĪÙħات
    -0.07
    bers
    -0.07
     Inflate
    -0.07
    resp
    -0.06
    лаÑĪ
    -0.06
    cout
    -0.06
    浦
    -0.06
    POSITIVE LOGITS
    weeney
    0.07
     Rough
    0.07
    blick
    0.07
    ognition
    0.07
    iddet
    0.07
    iating
    0.07
    ovice
    0.07
    edik
    0.06
    ekler
    0.06
    ãĥĥãĥĦ
    0.06
    Activations Density 0.005%

    No Known Activations