© 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 EvalsExportsinterp-engineNEWAPI 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. 105360
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and questions about timing and schedules

    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
    Æł
    -0.07
    LETTE
    -0.07
    INU
    -0.06
    /Instruction
    -0.06
    StringEncoding
    -0.06
    gom
    -0.06
    SSION
    -0.06
    _escape
    -0.06
    ÏĦεÏģ
    -0.06
    rint
    -0.06
    POSITIVE LOGITS
    addy
    0.08
     onset
    0.07
    est
    0.07
     earliest
    0.07
    ase
    0.06
    /if
    0.06
    ead
    0.06
    itzer
    0.06
     release
    0.06
    REA
    0.06
    Activations Density 0.004%

    No Known Activations