© 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. 95406
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal relationships, particularly regarding marriage and familial connections

    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
    erli
    -0.07
    iscrim
    -0.07
    ecast
    -0.07
    üçük
    -0.07
    isku
    -0.07
    ManagerInterface
    -0.07
    ebek
    -0.07
    dbus
    -0.07
    ordum
    -0.07
    abis
    -0.07
    POSITIVE LOGITS
     Morales
    0.07
    lant
    0.07
     dela
    0.06
     Bound
    0.06
     Picker
    0.06
     PD
    0.06
     info
    0.06
     helicopt
    0.06
    alth
    0.06
     tomorrow
    0.06
    Activations Density 0.003%

    No Known Activations