© 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. 15102
    Prev
    Next
    INDEX
    Explanations

    processes and techniques involved in welding and data encryption

    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
    ãĥ¼ãĥĭ
    -0.08
    izontal
    -0.07
    antity
    -0.07
    illion
    -0.07
    ebi
    -0.06
    osate
    -0.06
    phis
    -0.06
    itemap
    -0.06
    anium
    -0.06
    raud
    -0.06
    POSITIVE LOGITS
    ä¸Ģç§į
    0.07
     basically
    0.07
    ivist
    0.07
    KA
    0.06
     ìĿ¼ìłķ
    0.06
     typically
    0.06
    0.06
     literally
    0.06
     Zuk
    0.06
    bsites
    0.06
    Activations Density 0.064%

    No Known Activations