© 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 EvalsExportsinterp-engineNEWAPI 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. 54564
    Prev
    Next
    INDEX
    Explanations

    elements characteristic of product descriptions and recommendations

    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
     mur
    -0.06
    èĨ
    -0.06
    _traffic
    -0.06
     Din
    -0.06
    cha
    -0.06
     lie
    -0.06
    share
    -0.06
    quet
    -0.05
    ULO
    -0.05
    าห
    -0.05
    POSITIVE LOGITS
    opis
    0.08
    eking
    0.08
    iceps
    0.07
    ä¸Ī
    0.07
    寸
    0.07
    TestCategory
    0.07
     closures
    0.07
    erdem
    0.07
    _WM
    0.07
     اÙĦÙĨس
    0.07
    Activations Density 0.009%

    No Known Activations