© 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. 9-LLAMASCOPE-RES-131K
    11. 96448
    Prev
    Next
    INDEX
    Explanations

    references to data structures or elements in databases and spreadsheets

    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
    elter
    -0.06
    ÑĪа
    -0.06
    .Exit
    -0.06
    å¥ī
    -0.06
    ysa
    -0.06
    ollision
    -0.06
    ullan
    -0.06
    Cad
    -0.06
    edn
    -0.06
    ÏĮγ
    -0.06
    POSITIVE LOGITS
    ãĤ¹ãĥ¬
    0.07
    оÑĢон
    0.07
    jure
    0.06
     Äijâu
    0.06
    ance
    0.06
    ëħ¼
    0.06
    deaux
    0.06
     Ellis
    0.06
    ire
    0.06
    andle
    0.05
    Activations Density 0.001%

    No Known Activations