© 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. 5-LLAMASCOPE-RES-131K
    11. 125959
    Prev
    Next
    INDEX
    Explanations

    repeated articles and definite nouns in a context

    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
     âĹİ
    -0.07
    arna
    -0.07
     sublic
    -0.07
    ochen
    -0.07
    uesta
    -0.07
    mah
    -0.07
    é«ĺæ¸ħ
    -0.06
    //{{
    -0.06
    resse
    -0.06
    enas
    -0.06
    POSITIVE LOGITS
    odb
    0.06
    ECT
    0.06
    ÑĦик
    0.06
    Ķ
    0.06
     اÙĦجدÙĬد
    0.06
     ect
    0.06
    discord
    0.06
    compat
    0.06
     regular
    0.06
    ê
    0.05
    Activations Density 0.142%

    No Known Activations