© 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. 83544
    Prev
    Next
    INDEX
    Explanations

    references to media, particularly in relation to cancer

    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
     Brown
    -0.06
    unsqueeze
    -0.06
     A
    -0.06
    ino
    -0.06
     Hur
    -0.06
    hur
    -0.06
     Fur
    -0.06
    ès
    -0.06
     Burke
    -0.05
    istro
    -0.05
    POSITIVE LOGITS
    lags
    0.08
    arget
    0.07
    .sax
    0.07
    Äįan
    0.07
    «a
    0.07
    paramref
    0.07
    ÑĩаÑģ
    0.07
    Äįas
    0.07
    (EC
    0.06
    earer
    0.06
    Activations Density 0.078%

    No Known Activations