© 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. 9-LLAMASCOPE-RES-131K
    11. 94832
    Prev
    Next
    INDEX
    Explanations

    significant and impactful statements or quotes

    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
    #Region
    -0.06
    /locale
    -0.06
    InnerText
    -0.06
    elay
    -0.06
    βολ
    -0.06
    .getContentPane
    -0.06
    ooter
    -0.06
    onen
    -0.06
    äm
    -0.06
    ogie
    -0.05
    POSITIVE LOGITS
    polator
    0.08
    VERTISE
    0.08
    μοÏħ
    0.07
     vac
    0.07
    _Static
    0.07
    kas
    0.07
     Decompiled
    0.06
    tees
    0.06
    usters
    0.06
    ä¹ĭä¸Ģ
    0.06
    Activations Density 0.076%

    No Known Activations