© 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. 9-LLAMASCOPE-RES-131K
    11. 99282
    Prev
    Next
    INDEX
    Explanations

    references to reality TV show elements and dynamics

    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
    quee
    -0.09
    stanov
    -0.09
    ilan
    -0.09
     اختÙĦ
    -0.08
    _UT
    -0.08
    IZER
    -0.08
    isel
    -0.08
    IDEO
    -0.07
    ãĤ¹ãĥĨãĤ£
    -0.07
    ANGLE
    -0.07
    POSITIVE LOGITS
     tense
    0.06
    imes
    0.06
     Cr
    0.06
     tension
    0.06
     reality
    0.06
     crew
    0.06
     UK
    0.06
     dry
    0.05
     present
    0.05
    oll
    0.05
    Activations Density 0.007%

    No Known Activations