© 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. 93729
    Prev
    Next
    INDEX
    Explanations

    programming-related structure and operations in code

    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
    âĶ
    -0.06
    dc
    -0.06
    oog
    -0.06
     bis
    -0.06
    pais
    -0.06
    real
    -0.06
    ÙħاÙħ
    -0.05
    madıģı
    -0.05
    wan
    -0.05
    -m
    -0.05
    POSITIVE LOGITS
     fitte
    0.09
    (**
    0.08
    chwitz
    0.08
    ikel
    0.08
    ({...
    0.08
    _TestCase
    0.07
     Redistributions
    0.07
    OffsetTable
    0.07
    .scalablytyped
    0.07
    ToSelector
    0.07
    Activations Density 0.016%

    No Known Activations