© 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. 125493
    Prev
    Next
    INDEX
    Explanations

    significant points and factors in the context of analysis or performance

    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
    Cascade
    -0.06
    cciones
    -0.06
    iggins
    -0.06
    thouse
    -0.06
    ções
    -0.06
    bern
    -0.06
    éra
    -0.06
    ÑijÑĤ
    -0.06
    quot
    -0.06
    fra
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.07
    918
    0.07
     fact
    0.06
     اÛĮÙĨÚ©Ùĩ
    0.06
     tab
    0.06
    çļĦæĺ¯
    0.06
    iÄį
    0.06
    izza
    0.06
    843
    0.06
    ãĥ¼ãĥĸ
    0.06
    Activations Density 0.033%

    No Known Activations