© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119181
    Prev
    Next
    INDEX
    Explanations

    programming-related elements, especially concerning key-value pairs and error handling

    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
    omik
    -0.08
    EXTERN
    -0.07
     relief
    -0.07
    wie
    -0.07
    oram
    -0.06
    ấu
    -0.06
     ech
    -0.06
     indu
    -0.06
    "crypto
    -0.06
    ToDevice
    -0.06
    POSITIVE LOGITS
    amate
    0.07
    ayet
    0.06
    ULA
    0.06
    ophage
    0.06
    afür
    0.06
    imed
    0.06
    ç¼
    0.06
    ula
    0.06
    igate
    0.06
    ither
    0.05
    Activations Density 0.012%

    No Known Activations