© 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. 55327
    Prev
    Next
    INDEX
    Explanations

    the phrase "full disclosure" and its variations in various contexts

    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
    desk
    -0.07
    imer
    -0.07
    andler
    -0.07
    704
    -0.06
    amb
    -0.06
    uur
    -0.06
    ugar
    -0.06
    odb
    -0.06
    assigned
    -0.06
    uc
    -0.06
    POSITIVE LOGITS
     full
    0.12
    /full
    0.10
    full
    0.10
    (full
    0.10
     Full
    0.10
     FULL
    0.09
    -full
    0.09
    Full
    0.09
    .full
    0.09
    FULL
    0.08
    Activations Density 0.018%

    No Known Activations