© 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. 40277
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures in a coding 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
    é±
    -0.10
    /*č↵
    -0.08
    تز
    -0.07
    ẻ
    -0.07
    Ø
    -0.07
    Í
    -0.07
    åİ
    -0.07
    Ấ
    -0.07
    asions
    -0.07
    uras
    -0.07
    POSITIVE LOGITS
    0.07
    ↵
    0.06
     xsi
    0.06
     spar
    0.06
    /-
    0.06
     Ly
    0.06
    overs
    0.05
    []
    0.05
     Jun
    0.05
    roma
    0.05
    Activations Density 0.007%

    No Known Activations