© 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. 59541
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or expressions

    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
    abal
    -0.07
    apest
    -0.07
    peak
    -0.07
    gether
    -0.07
    ávÄĽ
    -0.07
    aning
    -0.07
    eder
    -0.07
    RESS
    -0.07
    ovation
    -0.07
    @Web
    -0.07
    POSITIVE LOGITS
     Greens
    0.06
    иÑħ
    0.06
    rys
    0.06
    dam
    0.06
    abouts
    0.06
     nucle
    0.06
    ry
    0.05
     Gim
    0.05
    inine
    0.05
     bordered
    0.05
    Activations Density 0.006%

    No Known Activations