© 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. 121266
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
    lesai
    -0.06
    lasses
    -0.06
    roupon
    -0.05
    ottes
    -0.05
    aida
    -0.05
    amburger
    -0.05
     transformed
    -0.05
    ales
    -0.05
    hei
    -0.05
    roduced
    -0.05
    POSITIVE LOGITS
     answering
    0.08
    orz
    0.07
    ujeme
    0.07
    ENDED
    0.07
    nost
    0.07
    AZY
    0.07
    .CopyTo
    0.07
     answers
    0.07
    à¹ĥห
    0.07
    minute
    0.07
    Activations Density 0.008%

    No Known Activations