© 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. 15-LLAMASCOPE-RES-131K
    11. 62483
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or comparison

    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
     aspect
    -0.06
     beyond
    -0.06
    bo
    -0.06
    /slick
    -0.05
     exactly
    -0.05
     Aspect
    -0.05
    isque
    -0.05
     thanks
    -0.05
     Lage
    -0.05
     liqu
    -0.05
    POSITIVE LOGITS
    than
    0.09
     than
    0.08
    -than
    0.08
    _than
    0.07
    antan
    0.07
    rik
    0.07
    ạc
    0.07
    $MESS
    0.07
    INTR
    0.06
     než
    0.06
    Activations Density 0.005%

    No Known Activations