© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95047
    Prev
    Next
    INDEX
    Explanations

    references to cities and their attributes

    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
    vid
    -0.07
    ogo
    -0.07
    riet
    -0.07
    .kotlin
    -0.06
    £
    -0.06
    858
    -0.06
    JECT
    -0.06
    Dll
    -0.05
    ules
    -0.05
     compl
    -0.05
    POSITIVE LOGITS
    enville
    0.07
    cen
    0.07
    furt
    0.07
    ål
    0.06
    bury
    0.06
     Greenwood
    0.06
    tokenizer
    0.06
    emoc
    0.06
    orque
    0.06
    à¸Ĺรà¸ĩ
    0.06
    Activations Density 0.017%

    No Known Activations