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

    Neuronpedia

    Jacobian LensNEW
    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. 16538
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and fitness

    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
    olate
    -0.07
    Å©
    -0.06
    antha
    -0.06
    ç¬Ķ
    -0.06
    à¤ķन
    -0.06
    Ìģt
    -0.06
    usk
    -0.06
     backpack
    -0.06
     overhe
    -0.06
    mong
    -0.06
    POSITIVE LOGITS
     weight
    0.09
     lifestyle
    0.09
     weigh
    0.08
     Lifestyle
    0.08
    fitness
    0.08
     Obesity
    0.08
     metabolic
    0.07
    çĺ
    0.07
     obesity
    0.07
     fitness
    0.07
    Activations Density 0.010%

    No Known Activations