© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57002
    Prev
    Next
    INDEX
    Explanations

    access and references to online resources

    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
    undy
    -0.06
     Cla
    -0.06
     TM
    -0.06
    812
    -0.05
    .goto
    -0.05
     below
    -0.05
     EM
    -0.05
     Aston
    -0.05
     Je
    -0.05
     Jur
    -0.05
    POSITIVE LOGITS
    ÎŃλ
    0.07
    DisplayStyle
    0.07
    IEW
    0.07
    ãĥĨãĥ«
    0.07
    ì¹´ëĿ¼
    0.07
    cesso
    0.06
    uden
    0.06
    iew
    0.06
    çĬ
    0.06
     '">
    0.06
    Activations Density 0.024%

    No Known Activations