© 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. 104970
    Prev
    Next
    INDEX
    Explanations

    references to specific political entities or geographical regions

    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
    ento
    -0.07
    oir
    -0.07
    åĪ°çļĦ
    -0.06
    uit
    -0.06
    ernet
    -0.06
    /her
    -0.06
    berry
    -0.06
    adera
    -0.06
    inge
    -0.06
    ãĥįãĥ«
    -0.05
    POSITIVE LOGITS
    -wide
    0.12
    wide
    0.10
    /Foundation
    0.09
    Å¡tÃŃ
    0.08
     اÙĦÙħتØŃدة
    0.07
     addCriterion
    0.07
    Wunused
    0.07
    ispecies
    0.07
    als
    0.07
    /Common
    0.07
    Activations Density 0.039%

    No Known Activations