© 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. 103123
    Prev
    Next
    INDEX
    Explanations

    numerical references to episodes in a TV series

    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
     (č↵
    -0.08
    -await
    -0.08
     >č↵
    -0.08
    oreach
    -0.07
    edor
    -0.07
     önünde
    -0.07
    (arc
    -0.07
    dcc
    -0.07
    /INFO
    -0.07
     PROCUREMENT
    -0.07
    POSITIVE LOGITS
     Anchor
    0.06
    .intellij
    0.06
    202
    0.06
    ,
    0.06
     primary
    0.06
     ago
    0.05
     Lia
    0.05
    ers
    0.05
    ;
    0.05
    insky
    0.05
    Activations Density 0.001%

    No Known Activations