© 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. 84357
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and scholarly bodies

    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
    KANJI
    -0.07
    íķĻê³¼
    -0.07
    ReadWrite
    -0.07
    ìŀ¡
    -0.07
    edith
    -0.07
     обÑĭ
    -0.06
    exels
    -0.06
    nicas
    -0.06
     smÄĽ
    -0.06
    ensely
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĤ¹
    0.06
     ac
    0.06
    agger
    0.06
    acic
    0.06
     Rust
    0.06
    ADR
    0.06
     Druid
    0.05
    енÑı
    0.05
     Wahl
    0.05
     ê°Ģê¹Į
    0.05
    Activations Density 0.007%

    No Known Activations