© 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. 61740
    Prev
    Next
    INDEX
    Explanations

    interactions and relationships in the context of power dynamics

    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
    stub
    -0.08
    aldo
    -0.07
    atu
    -0.06
    ASC
    -0.06
    WB
    -0.06
    çĩĥ
    -0.06
     Welt
    -0.06
    infeld
    -0.06
     resisted
    -0.06
    Stub
    -0.06
    POSITIVE LOGITS
     charm
    0.08
     Charm
    0.07
     survival
    0.07
     appe
    0.07
     Survival
    0.07
     diplom
    0.07
     Appe
    0.07
    appe
    0.07
     plac
    0.07
     flattering
    0.07
    Activations Density 0.059%

    No Known Activations