© 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. 85867
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming concepts and data types

    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
    esto
    -0.06
     formally
    -0.06
    okia
    -0.06
    .RELATED
    -0.06
    rego
    -0.06
    ced
    -0.06
     defer
    -0.06
    adesh
    -0.06
    769
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
     Practical
    0.07
    syn
    0.06
    ear
    0.06
    amas
    0.06
     gezocht
    0.06
     opak
    0.06
    ttp
    0.06
    avn
    0.06
     Rib
    0.06
    fm
    0.06
    Activations Density 0.001%

    No Known Activations