© 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. 40541
    Prev
    Next
    INDEX
    Explanations

    terms related to web traffic and analytics

    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
    ENA
    -0.07
    cak
    -0.07
    ajar
    -0.07
    iminal
    -0.07
    ãģıãĤī
    -0.07
    podob
    -0.06
    žil
    -0.06
    ä¿Ĭ
    -0.06
    oppins
    -0.06
     æĬķ稿æĹ¥
    -0.06
    POSITIVE LOGITS
     attribution
    0.06
     Bing
    0.06
    ocaly
    0.06
    Attrib
    0.06
     Attribution
    0.06
     Sergei
    0.06
     recorded
    0.06
     impressions
    0.06
     Click
    0.06
     visits
    0.06
    Activations Density 0.002%

    No Known Activations