© 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. 103878
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming syntax and code structure

    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
    forth
    -0.08
    око
    -0.08
    лаж
    -0.07
     Arb
    -0.07
    λÏį
    -0.07
     Vib
    -0.07
     Buff
    -0.07
    ãĥ³ãĤº
    -0.07
    EDIA
    -0.07
    ples
    -0.07
    POSITIVE LOGITS
    290
    0.07
    ColumnsMode
    0.07
    addtogroup
    0.06
    defgroup
    0.06
    830
    0.06
    :`~
    0.06
    malink
    0.06
    anner
    0.06
     Exclusive
    0.06
    ¨ë¶Ģ
    0.06
    Activations Density 0.052%

    No Known Activations