© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121569
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising and community support efforts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     componentName
    -0.07
    ecta
    -0.07
     Jahr
    -0.07
     å¹´
    -0.07
    kah
    -0.06
    aidu
    -0.06
    ÃŃst
    -0.06
    Û²Û°Û²
    -0.06
    à¥įà¤
    -0.06
    uchos
    -0.06
    POSITIVE LOGITS
    ëĿ½
    0.09
     pledged
    0.06
    imet
    0.06
    аниÑĨ
    0.06
     donations
    0.06
    CJK
    0.06
     pledges
    0.06
    åĭŁ
    0.06
     popularity
    0.06
    onn
    0.06
    Activations Density 0.004%

    No Known Activations