© 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. 61592
    Prev
    Next
    INDEX
    Explanations

    terms related to government and legal matters

    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
    ائÙĦ
    -0.07
    ĮĴ
    -0.07
    NotSupportedException
    -0.07
    ninger
    -0.07
    esseract
    -0.07
    ?url
    -0.07
    :animated
    -0.07
    üss
    -0.07
    ĨĴ
    -0.06
    esser
    -0.06
    POSITIVE LOGITS
    -related
    0.07
     related
    0.07
    iani
    0.06
    related
    0.06
    astr
    0.06
    èĤ¡
    0.06
    oman
    0.06
    574
    0.06
     downstream
    0.06
     Anchor
    0.05
    Activations Density 0.001%

    No Known Activations