© 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. 93914
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to legal and law enforcement matters

    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
     honoring
    -0.12
     honored
    -0.12
     honors
    -0.12
     behavioral
    -0.11
     favored
    -0.11
     Harbor
    -0.10
     honor
    -0.10
     favor
    -0.10
     harbor
    -0.10
     favors
    -0.10
    POSITIVE LOGITS
     Canada
    0.19
    Toronto
    0.19
    .ca
    0.18
     Canadian
    0.18
     Canadians
    0.18
    Canada
    0.18
     Toronto
    0.18
     RCMP
    0.17
    Canadian
    0.17
     Winnipeg
    0.17
    Activations Density 1.228%

    No Known Activations