© 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 EvalsExportsAPI 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. 29034
    Prev
    Next
    INDEX
    Explanations

    terms related to processes and actions involving creation or transformation in various contexts

    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
    cio
    -0.09
    ãĥŃãĥ¼
    -0.08
    ãĥ¼ãĤ¹
    -0.08
    егоÑĢ
    -0.08
    rome
    -0.08
    errick
    -0.08
    [sizeof
    -0.08
    imu
    -0.08
    ãĤ´ãĥª
    -0.08
    rst
    -0.08
    POSITIVE LOGITS
     of
    0.12
     wise
    0.06
     dello
    0.06
    asing
    0.06
     của
    0.06
    Scaler
    0.05
    pping
    0.05
     unb
    0.05
    yn
    0.05
    g
    0.05
    Activations Density 0.077%

    No Known Activations