© 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. 58525
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional pain or vulnerability

    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
    251
    -0.07
     loving
    -0.07
    oppins
    -0.06
     enjoy
    -0.06
     enjoyment
    -0.06
    oter
    -0.06
     wink
    -0.06
     partner
    -0.06
    apiKey
    -0.06
     "
    -0.06
    POSITIVE LOGITS
     OnCollision
    0.08
    imir
    0.07
    fuck
    0.07
    _uc
    0.07
    /raw
    0.07
    .truth
    0.07
    .cookie
    0.07
    yo
    0.07
    attempt
    0.07
    olley
    0.07
    Activations Density 0.013%

    No Known Activations