© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87802
    Prev
    Next
    INDEX
    Explanations

    terms related to weight loss and health metrics

    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
    lic
    -0.07
    ubble
    -0.07
     Inhal
    -0.07
    ÌĤ
    -0.06
    pong
    -0.06
    ÄįnÃŃ
    -0.06
    ë³µì§Ģ
    -0.06
    _PB
    -0.06
    )reader
    -0.06
    ãĥ³ãĤ¸
    -0.06
    POSITIVE LOGITS
     weight
    0.09
     obese
    0.08
     participants
    0.08
     Weight
    0.08
     ob
    0.07
    RCT
    0.07
     Lean
    0.07
     overweight
    0.07
     Obesity
    0.07
     obesity
    0.07
    Activations Density 0.014%

    No Known Activations