© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate requests for information or proposals

    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
    gregate
    -0.07
    annes
    -0.07
    peek
    -0.07
    ÑĬ
    -0.06
    vern
    -0.06
    repid
    -0.06
    hog
    -0.06
    æĹıèĩªæ²»
    -0.06
    ãĥ³ãĤ¯
    -0.06
    EMS
    -0.06
    POSITIVE LOGITS
    ndl
    0.07
    htable
    0.06
    chester
    0.06
    Ñıб
    0.06
    ulis
    0.06
     Lazar
    0.06
    cco
    0.06
     TMPro
    0.06
    ayout
    0.06
    -floating
    0.06
    Activations Density 0.000%

    No Known Activations