© 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. 87909
    Prev
    Next
    INDEX
    Explanations

    references to low-calorie or healthier alternatives in food and beverages

    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
    enco
    -0.08
    _macros
    -0.06
    amac
    -0.06
    activex
    -0.06
    erece
    -0.06
     AS
    -0.06
    went
    -0.06
    _hyper
    -0.06
    Ñģол
    -0.06
    umpt
    -0.06
    POSITIVE LOGITS
    ucker
    0.08
    icode
    0.07
    mitt
    0.07
    ughs
    0.07
     pulse
    0.07
    vailability
    0.06
     terminal
    0.06
    thon
    0.06
     Pulse
    0.06
    terminal
    0.06
    Activations Density 0.000%

    No Known Activations