© 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. 31630
    Prev
    Next
    INDEX
    Explanations

    expressions and references related to supportive artistic communities

    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
    ookies
    -0.08
    xee
    -0.07
    tern
    -0.07
     Gap
    -0.06
    алÑİ
    -0.06
     barr
    -0.06
    leine
    -0.06
     몰
    -0.06
    æŃ
    -0.06
    omu
    -0.06
    POSITIVE LOGITS
     circles
    0.16
     circle
    0.12
     community
    0.11
    åľĪ
    0.11
     communities
    0.10
    circle
    0.09
    community
    0.09
    -circle
    0.09
    Circle
    0.08
     Circle
    0.08
    Activations Density 0.229%

    No Known Activations