© 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. 78849
    Prev
    Next
    INDEX
    Explanations

    terms related to microwave technology and its function

    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
    živ
    -0.07
     beyond
    -0.06
     Ø´ÙĪ
    -0.06
    odb
    -0.06
    ndata
    -0.06
    éĽ
    -0.05
     bullet
    -0.05
    481
    -0.05
     Bullet
    -0.05
     dispersed
    -0.05
    POSITIVE LOGITS
    ilis
    0.07
    ritel
    0.07
    illions
    0.07
    UBE
    0.06
    ongs
    0.06
    erence
    0.06
    vac
    0.06
    mland
    0.06
    æIJº
    0.06
    ams
    0.06
    Activations Density 0.001%

    No Known Activations