© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60674
    Prev
    Next
    INDEX
    Explanations

    web-related terms or references to online resources and support documentation

    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
    ynes
    -0.06
    ersen
    -0.06
    orners
    -0.06
    ãĥ³ãĥIJ
    -0.06
    uren
    -0.06
     hind
    -0.06
     Presented
    -0.06
    инов
    -0.06
     Bal
    -0.05
    mez
    -0.05
    POSITIVE LOGITS
    _FA
    0.08
     Trou
    0.08
     answered
    0.08
    support
    0.08
    faq
    0.07
    FAQ
    0.07
     troub
    0.07
    -supported
    0.07
    upported
    0.07
     Unsupported
    0.07
    Activations Density 0.002%

    No Known Activations