© 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. 94652
    Prev
    Next
    INDEX
    Explanations

    references to banks and hotels, particularly in relation to their services and characteristics

    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
    erce
    -0.07
    erer
    -0.07
    ORED
    -0.07
    actory
    -0.07
    isma
    -0.07
    åĥ
    -0.06
     Yates
    -0.06
    -bs
    -0.06
    outil
    -0.06
    CHandle
    -0.06
    POSITIVE LOGITS
    arin
    0.06
    MR
    0.05
    ycz
    0.05
    «
    0.05
    inki
    0.05
    appl
    0.05
    /java
    0.05
    Span
    0.05
     yours
    0.05
    walker
    0.05
    Activations Density 0.001%

    No Known Activations