© 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. 31534
    Prev
    Next
    INDEX
    Explanations

    expressions related to disclaimers or qualifications

    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
    amp
    -0.06
     practical
    -0.06
    ebra
    -0.06
    еле
    -0.06
    urry
    -0.06
    udge
    -0.06
    Sock
    -0.06
     consc
    -0.06
    onne
    -0.05
    gt
    -0.05
    POSITIVE LOGITS
     previous
    0.12
    previous
    0.10
    Previous
    0.10
     Previous
    0.09
     previously
    0.09
     earlier
    0.08
    (previous
    0.08
     prior
    0.08
    ulk
    0.07
     бÑĥдÑĮ
    0.07
    Activations Density 0.002%

    No Known Activations