© 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. 82987
    Prev
    Next
    INDEX
    Explanations

    text about packaging or sets of items

    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
    zu
    -0.08
    /stretch
    -0.07
    angi
    -0.07
    ormsg
    -0.07
    icast
    -0.07
     Bingo
    -0.07
    reach
    -0.07
    ÙĨاÙĨ
    -0.07
    yer
    -0.07
    нов
    -0.07
    POSITIVE LOGITS
    roupon
    0.08
    artment
    0.08
    au
    0.08
     deal
    0.07
    hetto
    0.07
    (package
    0.07
     thầu
    0.07
    mate
    0.07
    gt
    0.07
    à¹ģรà¸ģ
    0.07
    Activations Density 0.010%

    No Known Activations