© 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. 15-LLAMASCOPE-RES-131K
    11. 88963
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities

    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
    ingu
    -0.08
    uala
    -0.07
    925
    -0.06
    erate
    -0.06
    803
    -0.06
    icide
    -0.06
    uda
    -0.06
    ä¹
    -0.05
    901
    -0.05
    ihat
    -0.05
    POSITIVE LOGITS
     queryInterface
    0.09
    .gdx
    0.07
    LBL
    0.07
    arie
    0.06
     createState
    0.06
    :expr
    0.06
    unken
    0.06
     consum
    0.06
    WSC
    0.06
    Attachments
    0.06
    Activations Density 0.005%

    No Known Activations