© 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. 125268
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to user input handling and event management

    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
    ÅŁi
    -0.07
     è²
    -0.06
    ivi
    -0.06
    воз
    -0.06
    CAST
    -0.06
    .isPresent
    -0.06
    ÙĦاÙĦ
    -0.06
    ufact
    -0.06
    ili
    -0.06
    icense
    -0.06
    POSITIVE LOGITS
     submit
    0.10
     submission
    0.09
     Submit
    0.09
     form
    0.08
     submitting
    0.08
    -submit
    0.08
     submits
    0.08
    submit
    0.08
     onSubmit
    0.08
     handleSubmit
    0.07
    Activations Density 0.002%

    No Known Activations