© 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. 78015
    Prev
    Next
    INDEX
    Explanations

    lines of code related to user input handling

    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
    antha
    -0.08
    anner
    -0.07
    orst
    -0.07
    ãĤ»ãĥ³
    -0.07
    .ali
    -0.07
    _RGBA
    -0.07
    ullet
    -0.07
    sock
    -0.06
    lav
    -0.06
    ribly
    -0.06
    POSITIVE LOGITS
     quit
    0.09
     commands
    0.08
     controlling
    0.07
    .cmd
    0.07
     Commands
    0.07
    cmd
    0.07
    commands
    0.07
     control
    0.07
     actions
    0.06
    aye
    0.06
    Activations Density 0.188%

    No Known Activations