© 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. 9-LLAMASCOPE-RES-131K
    11. 94493
    Prev
    Next
    INDEX
    Explanations

    references to specific political figures and locations

    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
    ussen
    -0.07
    axon
    -0.06
     membranes
    -0.06
    ope
    -0.06
    cope
    -0.06
    vale
    -0.06
    èo
    -0.06
     heraus
    -0.06
    109
    -0.06
    (predicate
    -0.06
    POSITIVE LOGITS
    osl
    0.07
    аки
    0.07
    ียว
    0.06
    etz
    0.06
    اÙĨÚ¯
    0.06
    urgeon
    0.06
    .qml
    0.06
    ymoon
    0.06
    rage
    0.06
    nemonic
    0.06
    Activations Density 0.001%

    No Known Activations