© 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. 119789
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of art and culture

    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
     addCriterion
    -0.09
    _mC
    -0.08
    _mD
    -0.08
    _mB
    -0.08
    /epl
    -0.08
    Äįel
    -0.07
     ÃĿ
    -0.07
    hled
    -0.07
    -wsj
    -0.07
    [".
    -0.07
    POSITIVE LOGITS
     removeFrom
    0.06
    Ńå·ŀ
    0.06
     indeed
    0.06
    -a
    0.05
    âĢ¦
    0.05
    æ´²
    0.05
    âĢ¦↵
    0.05
    igel
    0.05
    ignet
    0.05
    ,↵
    0.05
    Activations Density 0.035%

    No Known Activations