© 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. 26835
    Prev
    Next
    INDEX
    Explanations

    numerical data and related metrics

    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
    è¡Ĩ
    -0.07
    åĽ£
    -0.07
    .getInteger
    -0.07
    arily
    -0.06
    ossa
    -0.06
    aste
    -0.06
    öz
    -0.06
    _rgba
    -0.06
     Scan
    -0.06
    awah
    -0.06
    POSITIVE LOGITS
    oje
    0.08
    isu
    0.07
    _GRANTED
    0.06
    ÄĻ
    0.06
    ense
    0.06
    ppers
    0.06
    ensa
    0.06
    force
    0.06
    bial
    0.06
    Äįan
    0.06
    Activations Density 0.000%

    No Known Activations