© 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. 39621
    Prev
    Next
    INDEX
    Explanations

    references to churches and historical buildings

    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
     Nar
    -0.06
     opt
    -0.06
    zsche
    -0.06
     ka
    -0.05
     mount
    -0.05
     sort
    -0.05
     veri
    -0.05
     Sort
    -0.05
    788
    -0.05
    nt
    -0.05
    POSITIVE LOGITS
    continued
    0.07
    akedown
    0.07
    ños
    0.07
    ега
    0.07
     remained
    0.07
    оваÑĢ
    0.07
     continued
    0.07
    BLE
    0.07
    NamedQuery
    0.07
    -Sah
    0.07
    Activations Density 0.018%

    No Known Activations