© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and historical facts

    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
    argent
    -0.07
    -qu
    -0.07
     ori
    -0.06
     ENTER
    -0.06
    PickerController
    -0.06
    ixels
    -0.06
    ãĤĪ
    -0.06
    ãĤīãģĹãģĦ
    -0.06
     wrists
    -0.06
    760
    -0.06
    POSITIVE LOGITS
    aghan
    0.07
    nin
    0.07
     zich
    0.06
    utex
    0.06
    OMPI
    0.06
    YRO
    0.06
     mole
    0.06
    upal
    0.06
     LSM
    0.06
    Enlarge
    0.06
    Activations Density 0.019%

    No Known Activations