© 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. 9-LLAMASCOPE-RES-131K
    11. 94069
    Prev
    Next
    INDEX
    Explanations

    terms related to the Angular framework and its versions

    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
    chine
    -0.07
    rych
    -0.07
    apos
    -0.07
    argent
    -0.07
    extra
    -0.07
    agle
    -0.07
    ruba
    -0.07
     çIJ
    -0.07
    hest
    -0.07
    bsd
    -0.07
    POSITIVE LOGITS
     refere
    0.06
    _HC
    0.06
    OnInit
    0.06
    ãģĦãģĦ
    0.06
    sand
    0.06
     circles
    0.06
    à¹Īาว
    0.05
     Pil
    0.05
     Ve
    0.05
    .xxx
    0.05
    Activations Density 0.002%

    No Known Activations