© 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. 84865
    Prev
    Next
    INDEX
    Explanations

    instances of "Leave" followed by a numerical value

    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
    cede
    -0.07
    ming
    -0.07
    aly
    -0.06
    ness
    -0.06
    rok
    -0.06
     <->
    -0.06
    ched
    -0.06
    engu
    -0.06
    .cn
    -0.06
    ÂŃn
    -0.06
    POSITIVE LOGITS
    uiten
    0.07
    292
    0.07
     noreferrer
    0.07
    vetica
    0.07
     bunch
    0.06
    antro
    0.06
    dens
    0.06
    inded
    0.06
    *)_
    0.06
     executing
    0.06
    Activations Density 0.003%

    No Known Activations