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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71133
    Prev
    Next
    INDEX
    Explanations

    phrases related to empathy and offering emotional support

    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
    alli
    -0.07
    lit
    -0.07
    bout
    -0.07
    alan
    -0.06
    รà¸ĸ
    -0.06
    ourg
    -0.06
    elli
    -0.06
    dej
    -0.06
    alten
    -0.06
    ån
    -0.06
    POSITIVE LOGITS
    marshall
    0.07
     approach
    0.07
     tact
    0.07
    æļĸ
    0.06
    imir
    0.06
    icits
    0.06
    isbury
    0.06
    zcze
    0.06
     Employ
    0.06
     disarm
    0.06
    Activations Density 0.028%

    No Known Activations