© 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. 28849
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic texts

    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
    isson
    -0.07
    owell
    -0.06
    layui
    -0.06
    -Compatible
    -0.06
    merc
    -0.06
    кÑĢа
    -0.06
    metis
    -0.06
    WARDED
    -0.05
    VML
    -0.05
    iciencies
    -0.05
    POSITIVE LOGITS
    --;
    0.07
     crim
    0.07
    utor
    0.07
    (parseFloat
    0.06
    iec
    0.06
    /moment
    0.06
    .Features
    0.06
    ãĥ¼ãĥª
    0.06
     Eh
    0.06
    ãĥ¥
    0.06
    Activations Density 0.021%

    No Known Activations