© 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. 116549
    Prev
    Next
    INDEX
    Explanations

    phrases that express totality or inclusiveness

    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
    lus
    -0.07
    ãģĭãĤĬ
    -0.07
    endez
    -0.07
    ofday
    -0.07
    ula
    -0.06
    erli
    -0.06
    Uploader
    -0.06
    _dll
    -0.06
    ozilla
    -0.06
    anoia
    -0.06
    POSITIVE LOGITS
     practical
    0.08
     intents
    0.08
    vos
    0.07
    renom
    0.06
     Practical
    0.06
     loose
    0.06
     reasons
    0.06
    ROT
    0.06
    änger
    0.06
    dac
    0.06
    Activations Density 0.005%

    No Known Activations