© 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. 118870
    Prev
    Next
    INDEX
    Explanations

    discussions related to change and adaptation 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
    rlen
    -0.08
    ppo
    -0.07
    -thumbnail
    -0.07
    markt
    -0.07
    tm
    -0.07
    heten
    -0.07
    ÙĪجÙĪد
    -0.07
     ÛĮÙĪتÛĮ
    -0.06
    ạm
    -0.06
    овеÑĢ
    -0.06
    POSITIVE LOGITS
     changed
    0.12
     change
    0.12
    change
    0.11
     changing
    0.11
    -changing
    0.11
     Change
    0.11
    Change
    0.10
     Changing
    0.10
    å¤īæĽ´
    0.10
     Changed
    0.10
    Activations Density 0.030%

    No Known Activations