© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85105
    Prev
    Next
    INDEX
    Explanations

    references to charitable donations and support for nonprofit organizations

    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
    owitz
    -0.08
    zel
    -0.07
    åºĹ
    -0.07
    acula
    -0.06
    foundland
    -0.06
     cann
    -0.06
    ĶåĽŀ
    -0.06
    еÑĢÑĪ
    -0.06
    ooter
    -0.06
    zech
    -0.06
    POSITIVE LOGITS
    edException
    0.07
     charities
    0.07
    usch
    0.07
     causes
    0.07
    .ng
    0.06
    rud
    0.06
    undi
    0.06
    âr
    0.06
     bake
    0.06
    inces
    0.06
    Activations Density 0.024%

    No Known Activations