© 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. 17370
    Prev
    Next
    INDEX
    Explanations

    negations or phrases expressing disagreement

    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
    ÏĦί
    -0.08
    ieee
    -0.07
    illis
    -0.07
    δή
    -0.07
     exce
    -0.07
    deme
    -0.07
    ystack
    -0.07
    ä¹Ī
    -0.06
    jos
    -0.06
    421
    -0.06
    POSITIVE LOGITS
     depending
    0.09
     alike
    0.07
     ones
    0.07
    atives
    0.07
     Operation
    0.06
     thereof
    0.06
    _PKG
    0.06
    depending
    0.06
    247
    0.06
    wf
    0.06
    Activations Density 0.010%

    No Known Activations