© 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. 130247
    Prev
    Next
    INDEX
    Explanations

    terms related to certification exams and related topics

    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
    oton
    -0.06
    OT
    -0.06
    ovo
    -0.06
    umann
    -0.06
     #:
    -0.05
    .BLL
    -0.05
    elman
    -0.05
    berger
    -0.05
    urdy
    -0.05
     ___
    -0.05
    POSITIVE LOGITS
    ãģĴ
    0.08
    ameleon
    0.07
    åĩ
    0.07
    dump
    0.07
    ieux
    0.07
    ’h
    0.07
    unks
    0.07
    ÑģоÑĤ
    0.07
     dumps
    0.06
    omain
    0.06
    Activations Density 0.002%

    No Known Activations