© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90618
    Prev
    Next
    INDEX
    Explanations

    references to current or trending topics, particularly in media contexts

    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
     infamous
    -0.07
    idal
    -0.06
    itia
    -0.06
    à¸Ńส
    -0.06
     Naz
    -0.06
     æŀĹ
    -0.05
     CAS
    -0.05
     Hamp
    -0.05
    ple
    -0.05
     tro
    -0.05
    POSITIVE LOGITS
    UNT
    0.07
    리ìĸ´
    0.07
    leftright
    0.07
    kov
    0.07
    deniz
    0.07
     -*-č↵
    0.07
    صات
    0.07
     tez
    0.07
    æľĹ
    0.07
    leigh
    0.07
    Activations Density 0.000%

    No Known Activations