© 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. 16390
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to definitions and similarities

    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
    anoia
    -0.07
    loquent
    -0.07
    ansi
    -0.07
    pedo
    -0.07
    comma
    -0.07
    pillar
    -0.06
    ultiply
    -0.06
    -gnu
    -0.06
    odos
    -0.06
    anje
    -0.06
    POSITIVE LOGITS
     words
    0.07
    (constants
    0.06
    words
    0.06
    æĤł
    0.06
    ives
    0.06
    imonial
    0.06
    ankind
    0.05
     alleged
    0.05
     naturally
    0.05
     informational
    0.05
    Activations Density 0.001%

    No Known Activations