© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4011
    Prev
    Next
    INDEX
    Explanations

    words that convey visual or auditory appeal, particularly those related to brightness and shimmer

    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
    233
    -0.08
    sst
    -0.08
    aday
    -0.07
    umed
    -0.07
    VisualStyle
    -0.07
    fty
    -0.07
    alsa
    -0.07
    isy
    -0.07
    æ¤įçī©
    -0.07
    æ¤į
    -0.06
    POSITIVE LOGITS
    -eyed
    0.09
     lights
    0.09
    ingly
    0.08
    -white
    0.08
     gold
    0.08
    -clean
    0.08
    -light
    0.08
     eyed
    0.08
    -star
    0.07
    gold
    0.07
    Activations Density 0.013%

    No Known Activations