© 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. 15-LLAMASCOPE-RES-131K
    6. 26507
    Prev
    Next
    INDEX
    Explanations

    references to dietary guidelines and nutrition-related controversies

    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
    .epam
    -0.07
    addtogroup
    -0.07
    uchar
    -0.06
     getattr
    -0.06
    retweeted
    -0.06
    _physical
    -0.06
    implify
    -0.06
    incy
    -0.06
    onDelete
    -0.06
    622
    -0.06
    POSITIVE LOGITS
    çĥ
    0.08
    enstein
    0.07
    strup
    0.07
    -ra
    0.07
     Heart
    0.06
    Tween
    0.06
    çķª
    0.06
     çķ
    0.06
    uida
    0.06
    -fat
    0.06
    Activations Density 0.005%

    No Known Activations