© 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. 88815
    Prev
    Next
    INDEX
    Explanations

    expressions of kindness and compassion

    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
    arbon
    -0.08
    gle
    -0.07
    ständ
    -0.07
    åŁŁ
    -0.06
    xing
    -0.06
    ngo
    -0.06
    ttp
    -0.06
    725
    -0.06
    stroy
    -0.06
    lage
    -0.06
    POSITIVE LOGITS
     towards
    0.07
     toward
    0.07
    /lo
    0.07
    íŀĪ
    0.07
    nature
    0.07
     Uy
    0.07
    UDGE
    0.07
    erg
    0.07
    /help
    0.06
    าà¸ģร
    0.06
    Activations Density 0.020%

    No Known Activations