© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    references to various types of physical pain and medical conditions

    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
    ebo
    -0.07
    erk
    -0.06
    IPH
    -0.06
    statt
    -0.06
    ollen
    -0.06
    byt
    -0.06
    raf
    -0.06
    åī¯
    -0.06
    polator
    -0.06
     Partial
    -0.06
    POSITIVE LOGITS
    ле
    0.07
    .bulk
    0.07
    area
    0.06
     area
    0.06
    arent
    0.06
    firm
    0.06
    icontrol
    0.06
    ÏĥοÏħ
    0.06
     Integr
    0.06
    (Grid
    0.06
    Activations Density 0.013%

    No Known Activations