© 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. 9-LLAMASCOPE-RES-131K
    6. 95057
    Prev
    Next
    INDEX
    Explanations

    terms related to weight and obesity

    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
    engkap
    -0.07
    dum
    -0.07
    ocre
    -0.07
     Zuk
    -0.07
    ister
    -0.06
    isch
    -0.06
    flag
    -0.06
    duct
    -0.06
    deniz
    -0.06
     alignment
    -0.06
    POSITIVE LOGITS
    ãĤĤãĤĬ
    0.06
     overall
    0.06
    ampton
    0.06
    ัà¹Ī
    0.06
    Venue
    0.06
    /people
    0.06
     loss
    0.06
    247
    0.06
    crest
    0.06
    OrNil
    0.06
    Activations Density 0.005%

    No Known Activations