© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104195
    Prev
    Next
    INDEX
    Explanations

    instances of kindness and compassion in social contexts

    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
    apos
    -0.08
    ahoma
    -0.08
    aldi
    -0.07
    -ts
    -0.07
    elin
    -0.07
    /stdc
    -0.07
    .exc
    -0.07
    gregate
    -0.07
    reck
    -0.07
    MMdd
    -0.07
    POSITIVE LOGITS
     improvis
    0.06
     prof
    0.06
     spontaneous
    0.06
     hourly
    0.06
     many
    0.06
     improvised
    0.06
     local
    0.06
     spontaneously
    0.06
     overnight
    0.05
     ad
    0.05
    Activations Density 0.007%

    No Known Activations