© 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. 77274
    Prev
    Next
    INDEX
    Explanations

    expressions of personal uncertainty and inquiries about status updates

    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
    оÑĤв
    -0.07
    .EventQueue
    -0.07
    Å©
    -0.07
    onte
    -0.07
    ntax
    -0.07
    ระ
    -0.06
    é«
    -0.06
    еком
    -0.06
    avour
    -0.06
    άÏĥ
    -0.06
    POSITIVE LOGITS
     ov
    0.07
     hyster
    0.06
     blood
    0.06
    DX
    0.06
     test
    0.06
     miscar
    0.06
     Laboratories
    0.06
     Pregnancy
    0.06
     Test
    0.06
    543
    0.06
    Activations Density 0.012%

    No Known Activations