© 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. 27152
    Prev
    Next
    INDEX
    Explanations

    mentions of news organization names

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    esco
    -0.08
    vider
    -0.07
    ereum
    -0.07
    ylene
    -0.07
     Columns
    -0.06
    ample
    -0.06
    øj
    -0.06
    SION
    -0.06
    eltas
    -0.06
    aterangepicker
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĩãĤ£
    0.07
     affiliate
    0.06
     Raq
    0.06
    .yang
    0.06
    ãĥįãĥĥãĥĪ
    0.06
     embargo
    0.06
    _taxonomy
    0.06
    -network
    0.06
    íĸ
    0.06
    CTest
    0.06
    Activations Density 0.014%

    No Known Activations