© 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. 17-LLAMASCOPE-RES-131K
    11. 71940
    Prev
    Next
    INDEX
    Explanations

    references to ethical standards and practices in research

    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
    anda
    -0.07
    shal
    -0.07
     Riot
    -0.06
    725
    -0.06
    ota
    -0.06
    <fieldset
    -0.06
     reluct
    -0.06
     inflamm
    -0.06
    539
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
     publishing
    0.08
    PubMed
    0.07
    Ñĸб
    0.06
    urious
    0.06
     quality
    0.06
    STM
    0.06
    ichtet
    0.06
     Cinder
    0.06
     journals
    0.06
     Universe
    0.06
    Activations Density 0.000%

    No Known Activations