© 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. 17-LLAMASCOPE-RES-131K
    11. 93368
    Prev
    Next
    INDEX
    Explanations

    Java method declarations and annotations

    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
    ãģĹãĤĩ
    -0.06
    ãĤ¸ãĤ¢
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    hurst
    -0.06
    áo
    -0.06
    (:,
    -0.06
    ByText
    -0.06
     recom
    -0.06
     Levy
    -0.06
    ç¨
    -0.06
    POSITIVE LOGITS
     ãģĿãģ®ä»ĸ
    0.08
    ONUS
    0.07
    agar
    0.07
    abis
    0.06
    radu
    0.06
    eper
    0.06
    εια
    0.06
    ikit
    0.06
    END
    0.06
     didReceiveMemoryWarning
    0.06
    Activations Density 0.013%

    No Known Activations