© 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. 104172
    Prev
    Next
    INDEX
    Explanations

    actions and behaviors related to indiscriminate use of power or authority

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     åĿ
    -0.07
    ieux
    -0.07
    zano
    -0.07
    :\/\/
    -0.07
     Merkezi
    -0.06
    Ùħت
    -0.06
    /help
    -0.06
    .swt
    -0.06
    .clean
    -0.06
    ustin
    -0.06
    POSITIVE LOGITS
     freely
    0.11
     rash
    0.08
     caution
    0.07
     prolific
    0.07
     liber
    0.07
     indiscrim
    0.07
    Broad
    0.07
    echa
    0.07
     Broad
    0.06
     careless
    0.06
    Activations Density 0.076%

    No Known Activations