© 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. 76955
    Prev
    Next
    INDEX
    Explanations

    references to microwave technology and related components

    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
    s
    -0.07
    hread
    -0.07
    ustin
    -0.06
    igmoid
    -0.06
    inho
    -0.06
    weight
    -0.06
    ãĥ³ãĥij
    -0.06
    uples
    -0.06
    غاÙĦ
    -0.06
    ож
    -0.06
    POSITIVE LOGITS
    ody
    0.07
    ett
    0.07
     oven
    0.07
    etas
    0.07
    zee
    0.07
    oven
    0.07
    olson
    0.07
    rowave
    0.06
    tower
    0.06
    /opt
    0.06
    Activations Density 0.004%

    No Known Activations