© 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. 128142
    Prev
    Next
    INDEX
    Explanations

    references to RNA and its related processes in genetics

    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
    openh
    -0.07
    åĪ»
    -0.07
    loor
    -0.07
    ngen
    -0.06
    leh
    -0.06
    mnop
    -0.06
    izo
    -0.06
    eniable
    -0.06
     componentDid
    -0.06
     باش
    -0.06
    POSITIVE LOGITS
     RN
    0.08
     RNA
    0.08
     mi
    0.08
     antis
    0.07
    RNA
    0.07
    Âłmi
    0.07
    (mi
    0.06
     targeting
    0.06
     targets
    0.06
     apt
    0.06
    Activations Density 0.032%

    No Known Activations