© 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. 61674
    Prev
    Next
    INDEX
    Explanations

    references to community and relationships

    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
    ootball
    -0.09
    ernity
    -0.09
    ationale
    -0.09
    èģĶç½ij
    -0.08
    Ưá»
    -0.08
    chn
    -0.08
    लब
    -0.08
    vor
    -0.08
    erdem
    -0.08
    UIAlertView
    -0.08
    POSITIVE LOGITS
     us
    0.07
     efforts
    0.07
     Roh
    0.06
     Tir
    0.06
    fully
    0.06
    1
    0.06
    us
    0.06
    663
    0.06
     ende
    0.06
     towards
    0.06
    Activations Density 0.015%

    No Known Activations