© 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. 89306
    Prev
    Next
    INDEX
    Explanations

    colons and sections of text that follow them

    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
    berger
    -0.07
    ÙĪاء
    -0.06
    aze
    -0.06
    quisite
    -0.06
     же
    -0.06
     Microsystems
    -0.06
    539
    -0.06
    719
    -0.06
    CAPE
    -0.06
    510
    -0.05
    POSITIVE LOGITS
     &#
    0.08
     '&#
    0.07
    ýt
    0.07
    dds
    0.07
    evi
    0.07
     â
    0.07
    &#
    0.07
     Ãĥ
    0.06
    hic
    0.06
    ÑĥнкÑĤ
    0.06
    Activations Density 0.016%

    No Known Activations