© 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. 60541
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of control or authority

    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
    rame
    -0.07
    uario
    -0.07
    792
    -0.07
    _sink
    -0.07
     DropIndex
    -0.07
    лив
    -0.07
    deen
    -0.06
    лива
    -0.06
     MemoryStream
    -0.06
    MITTED
    -0.06
    POSITIVE LOGITS
     control
    0.11
    /control
    0.10
    -control
    0.09
    control
    0.09
     Control
    0.09
    Control
    0.08
     CONTROL
    0.08
    (control
    0.08
    /power
    0.08
    CONTROL
    0.07
    Activations Density 0.009%

    No Known Activations