© 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. 77626
    Prev
    Next
    INDEX
    Explanations

    expressions related to adherence to rules or standards

    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
    utz
    -0.07
    anie
    -0.07
    cls
    -0.07
    steen
    -0.07
    ised
    -0.07
    cole
    -0.07
    ile
    -0.07
    uell
    -0.07
    ediator
    -0.07
    ceries
    -0.06
    POSITIVE LOGITS
    GGLE
    0.08
    antly
    0.08
    ably
    0.08
    evil
    0.07
    άÏĥ
    0.07
    519
    0.07
     rules
    0.06
    879
    0.06
    780
    0.06
    -invalid
    0.06
    Activations Density 0.002%

    No Known Activations