© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94425
    Prev
    Next
    INDEX
    Explanations

    references to eating or consumption

    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
    quent
    -0.07
    کا
    -0.07
    _legacy
    -0.07
    teki
    -0.06
     Mig
    -0.06
     Gale
    -0.06
    emouth
    -0.06
    onaut
    -0.06
    rece
    -0.06
    zano
    -0.06
    POSITIVE LOGITS
    hom
    0.06
     Ud
    0.06
    803
    0.06
    ĶåĽŀ
    0.05
    øre
    0.05
    ynchronously
    0.05
     seeds
    0.05
     whole
    0.05
    _FINE
    0.05
    acro
    0.05
    Activations Density 0.016%

    No Known Activations