© 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. 17-LLAMASCOPE-RES-131K
    11. 28978
    Prev
    Next
    INDEX
    Explanations

    error and exception handling terminology in code

    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
    象
    -0.07
    orc
    -0.06
    oub
    -0.06
    orno
    -0.06
    >Lorem
    -0.06
    ãĥ¼ãĥ¬
    -0.06
    /buttons
    -0.06
    istrat
    -0.06
    ystick
    -0.06
    odos
    -0.06
    POSITIVE LOGITS
     migrationBuilder
    0.07
     âĨĴ↵↵
    0.07
    ëĿ¼ëıĦ
    0.06
    òng
    0.06
    antis
    0.06
    /design
    0.06
    deck
    0.06
    alex
    0.06
     Trent
    0.06
    _bel
    0.06
    Activations Density 0.002%

    No Known Activations