© 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. 119153
    Prev
    Next
    INDEX
    Explanations

    references to art and culture, particularly their impact and ethical considerations

    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
    anter
    -0.07
    æľŁå¾ħ
    -0.07
    EMPL
    -0.07
    ocket
    -0.07
    oha
    -0.07
    äm
    -0.07
    Ñħа
    -0.07
     à¤ķब
    -0.07
    pla
    -0.07
    æľŁ
    -0.07
    POSITIVE LOGITS
     should
    0.09
     ought
    0.08
    should
    0.08
     deserves
    0.07
     deserve
    0.07
     shouldn
    0.07
     Should
    0.07
     Ath
    0.07
     nên
    0.06
    Should
    0.06
    Activations Density 0.028%

    No Known Activations