© 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 EvalsExportsinterp-engineNEWAPI 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. 69609
    Prev
    Next
    INDEX
    Explanations

    terms associated with shipping and maritime activities

    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
    icz
    -0.06
    аÑĢÑĩ
    -0.06
    orsche
    -0.06
    zp
    -0.06
    appers
    -0.05
    658
    -0.05
     Luft
    -0.05
    odie
    -0.05
    olt
    -0.05
     Turnbull
    -0.05
    POSITIVE LOGITS
     vessel
    0.11
     vessels
    0.10
     Clarkson
    0.09
     cargo
    0.09
     yard
    0.08
     merchant
    0.08
     Damen
    0.08
     ton
    0.07
     container
    0.07
     ste
    0.07
    Activations Density 0.030%

    No Known Activations