© 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. 96215
    Prev
    Next
    INDEX
    Explanations

    phrases associated with official announcements or reports

    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
    iso
    -0.07
    Ļ¨
    -0.06
    benh
    -0.06
     iso
    -0.06
    ster
    -0.06
    aby
    -0.06
    _SUPPORT
    -0.06
    ya
    -0.06
    ISTRIBUT
    -0.06
    éĽĦ
    -0.05
    POSITIVE LOGITS
    ackers
    0.07
    tweets
    0.07
    ÏĢοÏĦε
    0.07
    arias
    0.07
    _intr
    0.07
    omers
    0.07
    macros
    0.07
     Coverage
    0.07
    lak
    0.06
    ORIZ
    0.06
    Activations Density 0.005%

    No Known Activations