© 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. 55018
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance and impact of education

    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
    ubl
    -0.07
    uns
    -0.07
    ationship
    -0.07
    objects
    -0.07
    æĻ
    -0.06
    зÑĥ
    -0.06
    nech
    -0.06
    å¬
    -0.06
    alic
    -0.06
    iais
    -0.06
    POSITIVE LOGITS
     education
    0.07
    idla
    0.06
     impro
    0.06
    ìĬ¤íĭ°
    0.06
     later
    0.06
     doors
    0.06
     higher
    0.06
     economic
    0.06
     Education
    0.06
     lifelong
    0.06
    Activations Density 0.041%

    No Known Activations