© 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. 130276
    Prev
    Next
    INDEX
    Explanations

    messages and themes related to fear and authoritarianism

    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
    寿
    -0.09
    _PD
    -0.07
    ìŀIJìĿ¸
    -0.07
    acades
    -0.07
    à¹Ģà¸Ľà¸¥
    -0.07
    تÙĪ
    -0.07
     Shelf
    -0.07
    奴
    -0.07
    ynth
    -0.07
    atte
    -0.06
    POSITIVE LOGITS
     purification
    0.07
     restore
    0.06
     purity
    0.06
    .restore
    0.06
     restoring
    0.06
     å¤
    0.06
    udden
    0.06
     allegedly
    0.06
     interpretation
    0.06
    Restore
    0.06
    Activations Density 0.021%

    No Known Activations