© 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. 15-LLAMASCOPE-RES-131K
    11. 86100
    Prev
    Next
    INDEX
    Explanations

    phrases indicating organizational or institutional involvement and influence

    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
    úsqueda
    -0.08
    raç
    -0.08
    .scalablytyped
    -0.08
    vang
    -0.08
    ccione
    -0.07
    eton
    -0.07
    agnar
    -0.07
    raž
    -0.07
    enson
    -0.06
    sty
    -0.06
    POSITIVE LOGITS
     porr
    0.07
    oeff
    0.07
     consc
    0.07
    ฯ
    0.06
     plugged
    0.06
     technolog
    0.06
     bree
    0.06
     Brook
    0.06
     thu
    0.06
     Göz
    0.06
    Activations Density 0.016%

    No Known Activations