© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 61078
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Stef" or its variants 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
     rep
    -0.07
    ured
    -0.06
    vir
    -0.06
     FAQs
    -0.06
    HIR
    -0.06
     ÑģÑĤав
    -0.06
     relative
    -0.06
    ivy
    -0.06
     vir
    -0.06
     virt
    -0.06
    POSITIVE LOGITS
    enson
    0.09
    atal
    0.08
    tember
    0.08
    iah
    0.07
    ardown
    0.07
    eler
    0.07
    apl
    0.07
    ytt
    0.07
    ildren
    0.07
    uards
    0.07
    Activations Density 0.002%

    No Known Activations