© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    references to specific terms and phrases related to technical processes, personal experiences, and media context

    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
    ulan
    -0.07
    burger
    -0.06
     minority
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    omba
    -0.06
    imity
    -0.06
     Maher
    -0.06
    Ñĸз
    -0.06
    rab
    -0.06
    faq
    -0.06
    POSITIVE LOGITS
     gusto
    0.09
     intact
    0.09
     impunity
    0.08
     backing
    0.07
     regard
    0.07
    lac
    0.07
    stood
    0.07
    attached
    0.06
     Twist
    0.06
     inplace
    0.06
    Activations Density 0.305%

    No Known Activations