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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61676
    Prev
    Next
    INDEX
    Explanations

    references to exceptions or errors in a technical context

    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
     Sad
    -0.06
    751
    -0.06
    witch
    -0.06
     ith
    -0.06
     Rage
    -0.05
    Sad
    -0.05
    aka
    -0.05
    ARRANT
    -0.05
     Rust
    -0.05
    ейн
    -0.05
    POSITIVE LOGITS
    uxe
    0.08
    antee
    0.07
    ikut
    0.07
    ogne
    0.07
     Consort
    0.06
    heimer
    0.06
    oux
    0.06
    asso
    0.06
    barang
    0.06
     ero
    0.06
    Activations Density 0.011%

    No Known Activations