© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72881
    Prev
    Next
    INDEX
    Explanations

    references to media coverage and its perceived biases

    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
    bud
    -0.07
    ÑĩÑĥк
    -0.07
     BindingFlags
    -0.06
    .tap
    -0.06
    emoc
    -0.06
    .tie
    -0.06
     lawy
    -0.06
    rana
    -0.06
    ippi
    -0.06
    onya
    -0.06
    POSITIVE LOGITS
     coverage
    0.10
     reporting
    0.09
    /report
    0.08
    coverage
    0.08
     Coverage
    0.07
     assignment
    0.07
     Reporting
    0.07
     bias
    0.07
     editorial
    0.07
     Pin
    0.07
    Activations Density 0.031%

    No Known Activations