© 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. 116599
    Prev
    Next
    INDEX
    Explanations

    HTML and script tags in code

    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
    esse
    -0.06
    uries
    -0.06
    apo
    -0.06
    inks
    -0.06
     rub
    -0.06
     atomic
    -0.05
    ional
    -0.05
    gypt
    -0.05
     conce
    -0.05
    ãĥijãĥ³
    -0.05
    POSITIVE LOGITS
    ymbols
    0.07
    .openg
    0.07
     addCriterion
    0.07
    timeofday
    0.07
     ÙģرÙħاÙĨ
    0.07
    ippers
    0.07
    Injection
    0.07
    gba
    0.06
    ORITY
    0.06
    geme
    0.06
    Activations Density 0.000%

    No Known Activations