© 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. 128672
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and humility

    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
    åĨ·
    -0.08
    vyk
    -0.07
    -INF
    -0.07
    Inactive
    -0.07
    uai
    -0.07
    Æ¡
    -0.07
    intptr
    -0.07
    _Result
    -0.06
    æ±ł
    -0.06
     Shape
    -0.06
    POSITIVE LOGITS
     modest
    0.11
     insist
    0.07
     insists
    0.07
     insistence
    0.07
     insisted
    0.07
     protest
    0.07
     insisting
    0.07
     protests
    0.06
     protesting
    0.06
     resistance
    0.06
    Activations Density 0.025%

    No Known Activations