© 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. 70911
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional states or reflections on personal experiences

    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
     immediately
    -0.06
     sofort
    -0.06
    tras
    -0.06
    rame
    -0.06
     Immediately
    -0.06
     truncate
    -0.06
    .terminate
    -0.06
     zah
    -0.06
    acha
    -0.06
    ίοÏĤ
    -0.06
    POSITIVE LOGITS
     increasingly
    0.21
     gradually
    0.20
     slowly
    0.17
    æ¸IJ
    0.17
     dần
    0.16
     Increasing
    0.16
    è¶Ĭ
    0.15
     поÑģÑĤеп
    0.15
     gradual
    0.15
     increasing
    0.14
    Activations Density 0.010%

    No Known Activations