© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56126
    Prev
    Next
    INDEX
    Explanations

    references to art and its attributes

    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
    åı¬
    -0.08
    nete
    -0.07
     Illustrated
    -0.06
    abyrinth
    -0.06
    esk
    -0.06
    ستاÙĨ
    -0.06
    atik
    -0.06
    /ts
    -0.06
    iad
    -0.06
    -src
    -0.06
    POSITIVE LOGITS
    onz
    0.07
    201
    0.07
    icast
    0.06
    å®ŀ
    0.06
    PEnd
    0.06
     Hlav
    0.06
    ypress
    0.06
    -install
    0.06
     blown
    0.06
    _mD
    0.06
    Activations Density 0.028%

    No Known Activations