© 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. 16119
    Prev
    Next
    INDEX
    Explanations

    concepts related to change and transformation in various contexts

    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
    kea
    -0.07
    ewire
    -0.07
     permanently
    -0.07
    ertz
    -0.06
    cing
    -0.06
    istra
    -0.06
    eward
    -0.06
    лÑĥÑĪ
    -0.06
     rendez
    -0.06
     prematurely
    -0.06
    POSITIVE LOGITS
     changing
    0.14
    changing
    0.13
     Changing
    0.13
    Changing
    0.12
     different
    0.12
    -changing
    0.11
    ä¸įåIJĮçļĦ
    0.11
    åıĺåĮĸ
    0.11
     changes
    0.11
     change
    0.11
    Activations Density 0.033%

    No Known Activations