© 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. 126411
    Prev
    Next
    INDEX
    Explanations

    references to recovery, support, and community involvement in addiction contexts

    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
    ").↵↵
    -0.08
    .↵
    -0.08
    ï¼īãĢĤ↵↵
    -0.08
     ".↵
    -0.08
    ".↵
    -0.07
    ा।↵↵
    -0.07
    '.↵↵
    -0.07
    '.↵
    -0.07
    ".↵↵
    -0.07
    /*č↵
    -0.07
    POSITIVE LOGITS
     {}.
    0.13
    ãĢĤéĤ£
    0.11
    ++.
    0.10
    ãĢĤ大
    0.10
    `.
    0.10
    +.
    0.10
    ãĢĤå½ĵ
    0.10
    ãĢĤä»Ĭ
    0.10
    ।
    0.10
    ’.
    0.10
    Activations Density 1.760%

    No Known Activations