© 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. 121412
    Prev
    Next
    INDEX
    Explanations

    instances of contrast and conditions in statements

    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
    pell
    -0.06
    ake
    -0.06
    igest
    -0.06
    ae
    -0.06
    isor
    -0.06
    ีà¹Ī
    -0.06
    HRESULT
    -0.06
     Eck
    -0.06
    illo
    -0.06
    isi
    -0.06
    POSITIVE LOGITS
     when
    0.09
    when
    0.07
    erken
    0.07
    ris
    0.06
     obvious
    0.06
    vida
    0.06
     When
    0.06
     cuando
    0.06
    vid
    0.06
     upside
    0.06
    Activations Density 0.008%

    No Known Activations