© 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. 75283
    Prev
    Next
    INDEX
    Explanations

    function return statements across various programming languages

    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
    ichte
    -0.06
    ÏĢÏĮ
    -0.06
    leigh
    -0.06
    วà¸ĩ
    -0.06
    ui
    -0.06
    ederation
    -0.06
     bases
    -0.05
     dismant
    -0.05
    zw
    -0.05
    kke
    -0.05
    POSITIVE LOGITS
    ISE
    0.07
    \Migration
    0.07
    957
    0.07
    AUSE
    0.07
    -valu
    0.07
    URRED
    0.06
    vla
    0.06
     onDataChange
    0.06
     WARRANTY
    0.06
    inis
    0.06
    Activations Density 0.015%

    No Known Activations