© 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. 126959
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to errors and process management in systems

    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
    ffe
    -0.06
    InternalServerError
    -0.06
    olist
    -0.06
     extraction
    -0.06
    å´İ
    -0.06
     Extraction
    -0.06
    als
    -0.06
     Notre
    -0.06
    angi
    -0.06
    æĶ¯
    -0.06
    POSITIVE LOGITS
     buildup
    0.15
     accumulation
    0.15
     build
    0.15
     accumulate
    0.14
    build
    0.13
     accum
    0.13
    accum
    0.13
     Accum
    0.13
     Build
    0.12
     acum
    0.12
    Activations Density 0.091%

    No Known Activations