© 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. 15-LLAMASCOPE-RES-131K
    11. 103189
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategies and their implementation in various contexts

    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
    ahren
    -0.07
    ãĢģ
    -0.07
    cheid
    -0.07
    rosso
    -0.07
    erness
    -0.07
    undle
    -0.06
     serm
    -0.06
    ãģ¾ãģŁ
    -0.06
    oca
    -0.06
    æļ
    -0.06
    POSITIVE LOGITS
     resulted
    0.09
    apult
    0.07
    ç©´
    0.06
    çµIJæŀľ
    0.06
    _Result
    0.06
     Results
    0.06
     gave
    0.06
    Results
    0.06
     result
    0.06
     policies
    0.06
    Activations Density 0.087%

    No Known Activations