© 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. 126723
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies and their components

    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
    .CreateCommand
    -0.07
    gni
    -0.07
    каз
    -0.07
    ControlItem
    -0.07
    aska
    -0.07
    NIC
    -0.06
    jes
    -0.06
    Å©i
    -0.06
    xe
    -0.06
    iri
    -0.06
    POSITIVE LOGITS
    alone
    0.07
     dipl
    0.06
     Bris
    0.06
    ãĥ³ãĥĩ
    0.06
     US
    0.06
    ocommerce
    0.06
    Delimiter
    0.06
    ãĥ¼ãĤ¸
    0.06
     Desmond
    0.06
    edata
    0.06
    Activations Density 0.008%

    No Known Activations