© 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. 42732
    Prev
    Next
    INDEX
    Explanations

    expressions of longing or pleading

    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
    svp
    -0.07
     aforementioned
    -0.07
    icare
    -0.07
    unma
    -0.06
     errs
    -0.06
    Ð
    -0.06
    Ì
    -0.06
    ÑĮ
    -0.06
     yat
    -0.06
    à¸Ħว
    -0.06
    POSITIVE LOGITS
    usch
    0.07
     oppon
    0.06
    ÐłÐĺ
    0.06
     Partnership
    0.06
    ALES
    0.06
    ิà¸Ļà¸Ķ
    0.06
     ResourceType
    0.06
    té
    0.06
    amik
    0.06
    ÑħодиÑĤÑĮ
    0.06
    Activations Density 0.002%

    No Known Activations