© 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. 127264
    Prev
    Next
    INDEX
    Explanations

    code syntax and function calls in 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
    bons
    -0.07
    kov
    -0.06
     âĢ¦↵
    -0.06
     [âĢ¦]↵
    -0.06
    âĢ¦↵
    -0.06
    Ħ
    -0.06
    ï¼Į以åıĬ
    -0.06
    êu
    -0.06
    ings
    -0.06
    ousing
    -0.06
    POSITIVE LOGITS
     -*-č↵
    0.08
    .SizeType
    0.08
    isque
    0.08
    :init
    0.08
    Intialized
    0.07
    ---</
    0.07
    .PerformLayout
    0.07
    пÑĢимеÑĢ
    0.07
    chter
    0.07
    'gc
    0.07
    Activations Density 0.139%

    No Known Activations