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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127904
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to food-sharing events or gatherings

    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
     pastry
    -0.06
     world
    -0.06
    deen
    -0.06
    -Feb
    -0.06
    ulu
    -0.06
    reasonable
    -0.06
    Reducer
    -0.06
    wrap
    -0.06
    addons
    -0.06
    ivate
    -0.05
    POSITIVE LOGITS
     contributions
    0.10
     contribution
    0.08
     contribute
    0.08
     Contribution
    0.07
     contrib
    0.07
    abar
    0.07
     contributed
    0.07
    å°½
    0.07
    .contrib
    0.07
    ãĤ¯ãĥĪ
    0.07
    Activations Density 0.008%

    No Known Activations