© 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. 121637
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a need for transparency and accountability

    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
    _frm
    -0.06
    777
    -0.06
    rogram
    -0.06
    .localized
    -0.06
    á»ĩu
    -0.06
    owitz
    -0.06
    cloth
    -0.05
    cht
    -0.05
    555
    -0.05
    amil
    -0.05
    POSITIVE LOGITS
    boa
    0.07
     noreferrer
    0.07
     themselves
    0.07
     úspÄĽ
    0.06
    IRECTION
    0.06
    ê°ģ
    0.06
     Julien
    0.06
    åĿĬ
    0.06
    uzz
    0.06
    credit
    0.06
    Activations Density 0.027%

    No Known Activations