© 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. 84755
    Prev
    Next
    INDEX
    Explanations

    concepts related to genetic processes and mutations

    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
    ingleton
    -0.08
    à¹īำ
    -0.07
    itals
    -0.07
     Schro
    -0.07
    ebi
    -0.07
    ÑĦи
    -0.07
    reon
    -0.06
    ÏĢοÏį
    -0.06
    olume
    -0.06
    rsp
    -0.06
    POSITIVE LOGITS
     exchange
    0.10
    Exchange
    0.10
     Exchange
    0.09
     exchanges
    0.09
    _exchange
    0.08
    exchange
    0.08
     exchanging
    0.08
     exchanged
    0.08
     random
    0.07
    .exchange
    0.07
    Activations Density 0.010%

    No Known Activations