© 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. 121429
    Prev
    Next
    INDEX
    Explanations

    phrases that describe conditions or implications related to legal and administrative contexts

    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
    alis
    -0.07
    ELY
    -0.06
     så
    -0.06
    .tap
    -0.06
    kar
    -0.06
    .Serial
    -0.06
    enan
    -0.06
    æīĢ以
    -0.06
    lum
    -0.06
    é¾Ļ
    -0.06
    POSITIVE LOGITS
    ÃĹ↵↵
    0.08
    eme
    0.08
    ifix
    0.07
    ãng
    0.07
    ác
    0.07
     ti
    0.07
    celik
    0.07
    ensburg
    0.07
    vale
    0.06
    ÑĢод
    0.06
    Activations Density 0.017%

    No Known Activations