© 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. 121558
    Prev
    Next
    INDEX
    Explanations

    references to celebrity relationships and drama

    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
    radient
    -0.07
    uchos
    -0.06
    è¥
    -0.06
     autos
    -0.06
    luet
    -0.06
    å¥ı
    -0.06
    è¯ij
    -0.06
    رز
    -0.06
    keh
    -0.06
    okie
    -0.06
    POSITIVE LOGITS
     feud
    0.09
    @$
    0.08
     beef
    0.07
     interpol
    0.07
    è¾
    0.07
     mutual
    0.07
     Beef
    0.07
     wounds
    0.06
    ossip
    0.06
     responded
    0.06
    Activations Density 0.025%

    No Known Activations