© 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. 123396
    Prev
    Next
    INDEX
    Explanations

    abbreviations or codes related to classifications or categories

    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
    plevel
    -0.09
    TRGL
    -0.08
    Å¡t
    -0.08
    .;.;
    -0.08
    inspace
    -0.08
    lessly
    -0.08
     огÑĢа
    -0.08
     имÑĥ
    -0.08
    elerine
    -0.08
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
    POSITIVE LOGITS
    ed
    0.12
    i
    0.12
    s
    0.12
    er
    0.12
    zelf
    0.10
    y
    0.10
    o
    0.10
    a
    0.09
    Ø©
    0.09
    an
    0.09
    Activations Density 0.215%

    No Known Activations