© 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. 41625
    Prev
    Next
    INDEX
    Explanations

    terms related to food delivery and takeaway services

    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
    ç³»
    -0.07
    kal
    -0.07
    ea
    -0.06
    lei
    -0.06
    itesse
    -0.06
    ENTA
    -0.06
    _regularizer
    -0.06
    lek
    -0.06
    ains
    -0.06
    lest
    -0.06
    POSITIVE LOGITS
    /mail
    0.08
    pekt
    0.07
    dar
    0.07
    /callback
    0.07
    .libs
    0.07
    -exclusive
    0.07
    anol
    0.07
    stry
    0.07
    /free
    0.07
    opi
    0.07
    Activations Density 0.028%

    No Known Activations