© 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. 54533
    Prev
    Next
    INDEX
    Explanations

    key phrases and terms related to regulations, statements, and societal debates

    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
    Äįást
    -0.07
    allis
    -0.07
    unch
    -0.07
    stract
    -0.07
     ún
    -0.07
     poil
    -0.07
    Parsed
    -0.07
    çģµ
    -0.07
     tô
    -0.07
     dobr
    -0.07
    POSITIVE LOGITS
     have
    0.06
     McCarthy
    0.06
     become
    0.06
     will
    0.06
     has
    0.06
    adesh
    0.06
     Bryant
    0.06
     would
    0.06
     can
    0.06
    stadt
    0.06
    Activations Density 0.086%

    No Known Activations