© 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 EvalsExportsAPI 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. 82753
    Prev
    Next
    INDEX
    Explanations

    instances of communication and urgent messages

    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
    elor
    -0.07
    059
    -0.07
    elf
    -0.07
    ellas
    -0.07
    -wow
    -0.07
     addCriterion
    -0.07
    leting
    -0.06
    алÑİ
    -0.06
    .CustomButton
    -0.06
    ynet
    -0.06
    POSITIVE LOGITS
     Ald
    0.06
     news
    0.06
     reporting
    0.06
     urg
    0.06
     certified
    0.06
     kole
    0.06
    Fcn
    0.06
    ILT
    0.06
    swer
    0.06
    åijĬè¯ī
    0.06
    Activations Density 0.037%

    No Known Activations