© 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. 74384
    Prev
    Next
    INDEX
    Explanations

    references to different types of sauces and cooking methods

    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
    .LookAndFeel
    -0.07
    üç
    -0.07
    nesia
    -0.07
    å¥ij
    -0.07
    anje
    -0.07
    áng
    -0.07
    érc
    -0.07
    ovation
    -0.07
    =YES
    -0.07
    efon
    -0.06
    POSITIVE LOGITS
    vr
    0.07
    zn
    0.06
    ograph
    0.06
    eter
    0.06
    abra
    0.06
    qt
    0.06
    _apps
    0.06
    apple
    0.06
    anan
    0.06
    adr
    0.06
    Activations Density 0.012%

    No Known Activations