© 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. 53878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant actions or events

    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
    deen
    -0.10
    UCT
    -0.07
    undle
    -0.07
     targetType
    -0.07
    úmeros
    -0.07
     Bilg
    -0.07
     männer
    -0.07
    gado
    -0.07
    oard
    -0.07
    RenderTarget
    -0.07
    POSITIVE LOGITS
     Indiana
    0.07
    her
    0.06
     indeed
    0.06
     Oaks
    0.06
    ather
    0.06
     indispens
    0.06
     Pence
    0.05
     America
    0.05
     provid
    0.05
     coord
    0.05
    Activations Density 0.000%

    No Known Activations