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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3739
    Prev
    Next
    INDEX
    Explanations

    references to whole grain ingredients and their significance

    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
    riad
    -0.08
    eldorf
    -0.08
    reste
    -0.07
    sonian
    -0.07
    dash
    -0.07
    zÄħ
    -0.06
    reator
    -0.06
    anne
    -0.06
    acente
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
    /full
    0.08
    heart
    0.08
    meal
    0.07
    iser
    0.07
     lot
    0.07
    åIJ¦
    0.07
    /part
    0.07
    é½IJ
    0.07
    uga
    0.07
    foods
    0.07
    Activations Density 0.009%

    No Known Activations