© 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. 106212
    Prev
    Next
    INDEX
    Explanations

    time-related references and timestamps

    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
     d
    -0.07
     (
    -0.06
    o
    -0.06
     en
    -0.06
    ,
    -0.06
     Haz
    -0.06
    ed
    -0.06
     Naz
    -0.06
    als
    -0.05
     hung
    -0.05
    POSITIVE LOGITS
    ÏĦοι
    0.11
    ascript
    0.08
    RefCount
    0.07
    chwitz
    0.07
    bah
    0.07
    ìĹ¼
    0.07
     seins
    0.07
     çı
    0.07
    .bc
    0.07
    CanBe
    0.07
    Activations Density 0.004%

    No Known Activations