© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125821
    Prev
    Next
    INDEX
    Explanations

    terms associated with emotional expressions and sentiment

    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
    INY
    -0.07
    až
    -0.07
    enan
    -0.07
    λÏĮ
    -0.07
    onian
    -0.07
    anson
    -0.07
    oningen
    -0.07
    elan
    -0.07
    اÙĨس
    -0.07
    ansson
    -0.07
    POSITIVE LOGITS
    osti
    0.06
    ized
    0.06
    etto
    0.06
    rede
    0.06
     Sure
    0.06
    pais
    0.06
     Ground
    0.05
     Vaults
    0.05
    amus
    0.05
    문
    0.05
    Activations Density 0.001%

    No Known Activations