© 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. 79066
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to bounds and inequalities

    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
    elt
    -0.06
     Lon
    -0.06
     Dickinson
    -0.06
    car
    -0.06
    kel
    -0.06
    oda
    -0.06
    978
    -0.06
    let
    -0.06
    7
    -0.05
     headed
    -0.05
    POSITIVE LOGITS
    atform
    0.08
    berapa
    0.08
    ablish
    0.08
    $MESS
    0.08
    xed
    0.08
    oplay
    0.08
    ramework
    0.08
    elerik
    0.07
    erno
    0.07
    edly
    0.07
    Activations Density 0.053%

    No Known Activations