© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75956
    Prev
    Next
    INDEX
    Explanations

    academic titles and positions within the field of computer science and engineering

    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
    .portal
    -0.07
    @student
    -0.07
    abee
    -0.06
    ожд
    -0.06
    aments
    -0.06
    ÏįÏĢ
    -0.06
    omed
    -0.06
    ocab
    -0.06
     tick
    -0.06
    olah
    -0.06
    POSITIVE LOGITS
     Teaching
    0.07
     оÑĤк
    0.07
     teaching
    0.07
    Advertisement
    0.07
    ='<?
    0.06
    imals
    0.06
    clus
    0.06
     unten
    0.06
     defe
    0.06
    maal
    0.06
    Activations Density 0.017%

    No Known Activations