© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those associated with movement and object manipulation in 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
    CTL
    -0.07
    wo
    -0.07
    ÏģÏį
    -0.07
    Ùħز
    -0.07
    á»ĭ
    -0.07
    нообÑĢаз
    -0.06
    _Context
    -0.06
    олиÑĤ
    -0.06
    xo
    -0.06
    ivityManager
    -0.06
    POSITIVE LOGITS
    oras
    0.06
    inas
    0.06
    able
    0.06
    .deepcopy
    0.06
    erdale
    0.06
    /null
    0.06
    913
    0.06
    ora
    0.05
    .AddColumn
    0.05
    622
    0.05
    Activations Density 0.001%

    No Known Activations