© 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 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. 56185
    Prev
    Next
    INDEX
    Explanations

    elements related to tutorial content and completion

    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
    icari
    -0.07
     Lois
    -0.07
    immel
    -0.07
     Consort
    -0.06
    .struts
    -0.06
     Consortium
    -0.06
     IonicModule
    -0.06
    Ùģت
    -0.06
     æĿ¡
    -0.06
    uster
    -0.06
    POSITIVE LOGITS
    pek
    0.08
    ancode
    0.07
    zan
    0.07
     code
    0.07
    .code
    0.06
    nip
    0.06
    @click
    0.06
    .zip
    0.06
    éal
    0.06
     tutorial
    0.06
    Activations Density 0.011%

    No Known Activations