© 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. 15-LLAMASCOPE-RES-131K
    11. 88019
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction or grievances

    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
    ieux
    -0.09
    orthy
    -0.08
    rega
    -0.07
    (Gravity
    -0.07
    yles
    -0.07
    Ưá»
    -0.07
    _INCLUDE
    -0.07
    tep
    -0.07
    ReturnValue
    -0.07
    luet
    -0.07
    POSITIVE LOGITS
    izard
    0.07
    gain
    0.06
    parable
    0.06
    Care
    0.06
    éķ
    0.06
     blob
    0.05
    mund
    0.05
    capability
    0.05
    gel
    0.05
    Å
    0.05
    Activations Density 0.001%

    No Known Activations