© 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. 14580
    Prev
    Next
    INDEX
    Explanations

    phrases centered around the concept of purpose 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
    yang
    -0.07
    vers
    -0.07
    late
    -0.06
     late
    -0.06
    pons
    -0.06
    acht
    -0.06
    gon
    -0.06
     Late
    -0.06
    nect
    -0.06
    å¯
    -0.06
    POSITIVE LOGITS
    ktop
    0.08
    evin
    0.07
    ury
    0.07
    onium
    0.07
     existence
    0.06
    existence
    0.06
    punk
    0.06
     ÄĮer
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    ytut
    0.06
    Activations Density 0.012%

    No Known Activations