© 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. 15-LLAMASCOPE-RES-131K
    11. 27445
    Prev
    Next
    INDEX
    Explanations

    references to chromosomes and gender determination in plants

    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
    jet
    -0.07
    jde
    -0.07
     Fet
    -0.07
    outed
    -0.07
    unn
    -0.07
    verb
    -0.06
    resse
    -0.06
     бÑĢаÑĤ
    -0.06
    amic
    -0.06
    ollow
    -0.06
    POSITIVE LOGITS
    213
    0.06
     inheritance
    0.06
    copies
    0.06
     inherited
    0.06
    Ķ
    0.06
     copied
    0.06
     Uhr
    0.06
    aln
    0.06
    utex
    0.06
    atoon
    0.05
    Activations Density 0.004%

    No Known Activations