© 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. 82593
    Prev
    Next
    INDEX
    Explanations

    textual references to universities or educational institutions

    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
    thead
    -0.06
    ÂŃt
    -0.06
     Hamp
    -0.06
    ÑĮ
    -0.06
    Delete
    -0.06
    SKU
    -0.06
    igo
    -0.05
    WARDED
    -0.05
     do
    -0.05
    546
    -0.05
    POSITIVE LOGITS
    Copyright
    0.09
     Copyright
    0.09
    ihn
    0.09
     copyright
    0.08
     célib
    0.08
    .MixedReality
    0.08
    copyright
    0.08
    iliz
    0.07
    ẽ
    0.07
     meiden
    0.07
    Activations Density 0.020%

    No Known Activations