© 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. 9-LLAMASCOPE-RES-131K
    11. 97404
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming language syntax and 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
    ifact
    -0.06
    leh
    -0.06
    ftware
    -0.06
    AZE
    -0.06
    anoia
    -0.06
    tti
    -0.06
    aling
    -0.06
    allis
    -0.06
    anoi
    -0.06
    detect
    -0.06
    POSITIVE LOGITS
     Tod
    0.07
    adow
    0.06
    .nih
    0.06
    imde
    0.06
     Fat
    0.06
    ADOW
    0.06
    ãĥ¼ãĥķ
    0.06
     Caesar
    0.06
    tsy
    0.06
     Sim
    0.05
    Activations Density 0.001%

    No Known Activations