© 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. 62165
    Prev
    Next
    INDEX
    Explanations

    instances of words and phrases that express discontent or criticism towards situations or behaviors

    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
    anya
    -0.08
    IMS
    -0.07
    heel
    -0.07
    rika
    -0.07
    £
    -0.07
    lew
    -0.07
    er
    -0.07
    displayText
    -0.07
    preneur
    -0.07
    olean
    -0.07
    POSITIVE LOGITS
    ering
    0.08
    nowledge
    0.08
    nowled
    0.08
    ei
    0.08
    el
    0.07
    ea
    0.07
    ford
    0.07
    ered
    0.07
    efeller
    0.07
     st
    0.07
    Activations Density 0.012%

    No Known Activations