© 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. 118311
    Prev
    Next
    INDEX
    Explanations

    topics related to social and historical injustices

    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
    èĩ³
    -0.07
    uden
    -0.07
    afen
    -0.07
    หร
    -0.06
    lıģının
    -0.06
     меÑĢ
    -0.06
     Äįi
    -0.06
    atl
    -0.06
     lean
    -0.06
    stroy
    -0.06
    POSITIVE LOGITS
    ä¸Ķ
    0.11
     with
    0.10
    with
    0.07
    swith
    0.07
     preferably
    0.07
     whose
    0.07
     vỼi
    0.06
    ï¼ĮèĢĮä¸Ķ
    0.06
     WITH
    0.06
     -*-č↵
    0.06
    Activations Density 0.161%

    No Known Activations