© 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. 92980
    Prev
    Next
    INDEX
    Explanations

    terms related to benefits and compensation policies, particularly for mothers and disabled individuals

    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
     indir
    -0.06
    lemn
    -0.06
    ãĤ¸
    -0.06
    acas
    -0.06
     kab
    -0.06
    ané
    -0.06
    pell
    -0.06
    dash
    -0.06
     доз
    -0.06
    angling
    -0.06
    POSITIVE LOGITS
     covered
    0.07
     perd
    0.07
    COVER
    0.07
     Temporary
    0.07
     Coverage
    0.06
    -covered
    0.06
     cover
    0.06
    \grid
    0.06
    covered
    0.06
    BaseContext
    0.06
    Activations Density 0.005%

    No Known Activations