© 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. 127235
    Prev
    Next
    INDEX
    Explanations

    instances of the word "real" in various contexts

    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
    sburg
    -0.08
    .au
    -0.07
    owitz
    -0.07
    exion
    -0.07
    ức
    -0.07
     mere
    -0.07
    ÅĦ
    -0.07
    optera
    -0.07
    spb
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
    igned
    0.13
    ign
    0.12
    ignment
    0.12
    -life
    0.11
     estate
    0.10
     McCoy
    0.10
    ationship
    0.10
    -time
    0.09
    locate
    0.09
     real
    0.09
    Activations Density 0.023%

    No Known Activations