© 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. 55585
    Prev
    Next
    INDEX
    Explanations

    terms associated with artistic value and significance

    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
    odor
    -0.07
    Themes
    -0.06
     Public
    -0.06
    /themes
    -0.05
    Ïįν
    -0.05
    idis
    -0.05
    ç¸
    -0.05
    ''''
    -0.05
    j
    -0.05
     Themes
    -0.05
    POSITIVE LOGITS
    YRO
    0.08
    oppable
    0.07
    xima
    0.07
    ä¸Ģ页
    0.07
    REFERRED
    0.07
    isphere
    0.07
    BCM
    0.07
    OUCH
    0.07
    ÃŃch
    0.07
    etto
    0.07
    Activations Density 0.005%

    No Known Activations