© 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. 17056
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "exemplify" and its forms

    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
    ffective
    -0.08
    evity
    -0.07
    vince
    -0.07
    ÅĤo
    -0.07
    view
    -0.07
    SEC
    -0.06
    lords
    -0.06
    fern
    -0.06
    earing
    -0.06
    liness
    -0.06
    POSITIVE LOGITS
     Ñģобой
    0.08
    nda
    0.07
    ropri
    0.07
    ively
    0.06
     typ
    0.06
    metros
    0.06
    OnError
    0.06
    uber
    0.06
    mos
    0.06
    rador
    0.06
    Activations Density 0.004%

    No Known Activations