© 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. 81927
    Prev
    Next
    INDEX
    Explanations

    instances of communication and interactions among individuals

    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
    onen
    -0.07
    olit
    -0.07
     PROCUREMENT
    -0.07
    #
    -0.07
    hei
    -0.07
    actal
    -0.07
    ezi
    -0.07
    sono
    -0.07
    /Gate
    -0.07
    rray
    -0.07
    POSITIVE LOGITS
     conf
    0.12
     trusted
    0.10
     sharing
    0.09
     leaking
    0.08
     telling
    0.07
     shared
    0.07
     Trusted
    0.07
     tell
    0.07
     share
    0.07
     secrets
    0.07
    Activations Density 0.068%

    No Known Activations