© 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. 89235
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or petitions

    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
    ensen
    -0.06
    quier
    -0.06
    eree
    -0.06
     Toe
    -0.06
    halb
    -0.05
     unser
    -0.05
     Beste
    -0.05
    CKER
    -0.05
    Toe
    -0.05
    apı
    -0.05
    POSITIVE LOGITS
    igham
    0.07
     поÑĢÑıд
    0.07
    ukes
    0.07
    ãĤ¤ãĥ³ãĤ¿
    0.06
     monitor
    0.06
    edException
    0.06
    ħĮ
    0.06
    Defaults
    0.06
    etyl
    0.06
    topic
    0.06
    Activations Density 0.012%

    No Known Activations