© 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. 88375
    Prev
    Next
    INDEX
    Explanations

    references to legal or bureaucratic processes, especially related to name changes and documentation

    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
    ondon
    -0.07
    mgr
    -0.07
     pás
    -0.07
    åĨ
    -0.07
    è¿Ľ
    -0.06
    olit
    -0.06
    probe
    -0.06
     ÄijÆ°a
    -0.06
    eti
    -0.06
    spin
    -0.06
    POSITIVE LOGITS
     change
    0.07
    (change
    0.07
    .Change
    0.07
    -change
    0.07
    change
    0.07
    Changing
    0.07
     Changing
    0.06
    handleChange
    0.06
     perman
    0.06
    _change
    0.06
    Activations Density 0.005%

    No Known Activations