© 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. 9-LLAMASCOPE-RES-131K
    11. 96981
    Prev
    Next
    INDEX
    Explanations

    references to systemic issues and concerns about social structures

    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
    ohn
    -0.07
    üt
    -0.07
    cher
    -0.07
    ivr
    -0.07
    chen
    -0.07
    æī¿
    -0.06
    ustin
    -0.06
    iolet
    -0.06
    ãģĭãģ®
    -0.06
     Nhất
    -0.06
    POSITIVE LOGITS
     even
    0.07
     dign
    0.06
    	HX
    0.06
    ãģĸ
    0.06
    _literals
    0.06
    _serial
    0.06
    .GetChild
    0.06
    άνα
    0.06
    ocos
    0.06
    FAST
    0.06
    Activations Density 0.060%

    No Known Activations