© 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. 124541
    Prev
    Next
    INDEX
    Explanations

    references to academic majors and programs of study

    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
    .Flush
    -0.08
    -urlencoded
    -0.07
    enden
    -0.07
    isphere
    -0.07
    ilk
    -0.07
    opleft
    -0.07
    lest
    -0.07
    AMS
    -0.07
    ivy
    -0.07
    ifar
    -0.07
    POSITIVE LOGITS
    ing
    0.08
    pic
    0.07
    uffman
    0.06
    ships
    0.06
    551
    0.06
     Matcher
    0.06
     san
    0.06
    347
    0.06
    /min
    0.06
    545
    0.06
    Activations Density 0.004%

    No Known Activations