© 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. 77105
    Prev
    Next
    INDEX
    Explanations

    language related to legal and international obligations

    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
     Attribution
    -0.06
    ообÑĢаз
    -0.06
    ALCHEMY
    -0.06
     меÑĩ
    -0.06
     wet
    -0.06
    endale
    -0.06
     gep
    -0.06
    IVAL
    -0.06
    eth
    -0.06
    okie
    -0.06
    POSITIVE LOGITS
     international
    0.10
    international
    0.09
    lacak
    0.09
     internacional
    0.08
     harmon
    0.08
    åĽ½éĻħ
    0.08
     EU
    0.08
     International
    0.07
     commitments
    0.07
    åĽ½éļĽ
    0.07
    Activations Density 0.029%

    No Known Activations