© 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. 15-LLAMASCOPE-RES-131K
    11. 90366
    Prev
    Next
    INDEX
    Explanations

    instances of the word "filled" and similar terms suggesting abundance or density

    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
    arem
    -0.07
    iris
    -0.07
    oli
    -0.06
    Tube
    -0.06
     nÃło
    -0.06
    ÏĦÏĥ
    -0.06
     Recorder
    -0.06
    WWW
    -0.06
     Tubes
    -0.06
    smith
    -0.06
    POSITIVE LOGITS
    ymmetric
    0.07
    æĪĴ
    0.06
    502
    0.06
    zier
    0.06
     entire
    0.06
    kke
    0.06
    rz
    0.06
    Ìī
    0.06
    лиÑĪком
    0.06
    ãĤ¶ãĥ¼
    0.06
    Activations Density 0.045%

    No Known Activations