© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120384
    Prev
    Next
    INDEX
    Explanations

    block structures or control statements in programming 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
    iner
    -0.08
    ortho
    -0.08
    enze
    -0.08
    ogl
    -0.08
    amil
    -0.08
    ych
    -0.08
    ưỡng
    -0.08
    ç·Ĵ
    -0.08
    ↵↵
    -0.07
    ê´
    -0.07
    POSITIVE LOGITS
     transition
    0.06
    -
    0.06
     ded
    0.06
     Cook
    0.06
     simply
    0.05
     effect
    0.05
     fault
    0.05
    lub
    0.05
    âĢ¦
    0.05
    /
    0.05
    Activations Density 0.024%

    No Known Activations